© 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. 13501
    Prev
    Next
    INDEX
    Explanations

    specific objects and components related to products or equipment

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

    physical protrusions, bulges, or structural features that stick out from surfaces.

    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
    URLException
    -0.36
     unggul
    -0.31
     NavController
    -0.30
     layui
    -0.29
     során
    -0.27
     rural
    -0.27
    AndroidJUnit
    -0.27
     metu
    -0.26
    Identyfik
    -0.26
     trotz
    -0.25
    POSITIVE LOGITS
     thingy
    0.84
    parsedMessage
    0.78
    LookAnd
    0.73
     attached
    0.71
    behind
    0.68
     affixed
    0.68
     underneath
    0.68
     behind
    0.68
    attached
    0.67
     beneath
    0.65
    Activations Density 0.799%

    No Known Activations