© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 5445
    Prev
    Next
    INDEX
    Explanations

    geographical locations and their connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    geographic locations and place names, particularly in Illinois.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    geographic location names, particularly in Illinois trail and park descriptions, with strongest activations for place names, route numbers, and directional prepositions that specify locations.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of specific geographic place names and route references—especially trails, parks, roads, rivers, towns—and the locational phrases that connect them in descriptions.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     invokingState
    -0.60
     CURIAM
    -0.52
    /**
    -0.48
    jsii
    -0.46
    brainly
    -0.44
    niosek
    -0.44
     ویکی‌پدیا
    -0.42
     termica
    -0.42
    verifyException
    -0.41
     masjid
    -0.40
    POSITIVE LOGITS
     Aberdeen
    0.50
    Aberdeen
    0.48
    XmlAccessType
    0.47
    arkov
    0.43
    山形
    0.42
    WaitGroup
    0.42
    MessageTagHelper
    0.40
     Darlington
    0.39
     Харь
    0.38
     Flin
    0.38
    Activations Density 0.252%

    No Known Activations