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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 7616
    Prev
    Next
    INDEX
    Explanations

    spatial orientation and depth-related terms

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

    spatial position indicators like "underneath," "below," "above," "ahead," "in front," and "top."

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    the word "below" and spatial/directional positioning language.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
     propOrder
    -0.66
    msgTypes
    -0.58
    ंदीखरीदारी
    -0.56
    SharedCtor
    -0.55
     nakalista
    -0.53
    évaluateur
    -0.53
     CanadaChoose
    -0.53
    findpost
    -0.52
    tanleria
    -0.51
    цездатний
    -0.51
    POSITIVE LOGITS
    jspx
    0.55
     niego
    0.45
     immédi
    0.43
    wards
    0.42
    stairs
    0.41
    ward
    0.41
     tuyo
    0.41
    ‌تر
    0.40
     него
    0.39
     себя
    0.39
    Activations Density 0.419%

    No Known Activations