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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2707
    Prev
    Next
    INDEX
    Explanations

    URLs and references to GitHub and other online resources

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

    URLs and web links, particularly GitHub repository paths and domain structures.

    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
    ствием
    -0.47
     driver
    -0.44
     gallery
    -0.43
     Partner
    -0.42
     mong
    -0.41
    üller
    -0.41
     Spart
    -0.41
     Cessna
    -0.41
     model
    -0.40
     cluster
    -0.40
    POSITIVE LOGITS
    CodeAttribute
    0.48
     almohada
    0.47
    Enllaces
    0.47
     tartalomajánló
    0.47
    TagMode
    0.46
    developers
    0.46
     toalla
    0.45
    клопе
    0.45
     válvula
    0.45
    //
    0.45
    Activations Density 0.612%

    No Known Activations