© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 5413
    Prev
    Next
    INDEX
    Explanations

    script syntax and structure elements related to programming or coding errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     = 
    -0.59
     skall
    -0.56
     Whilst
    -0.53
    Whilst
    -0.46
    -0.45
    войства
    -0.44
    \#
    -0.43
     szükség
    -0.43
     diatas
    -0.42
    -0.42
    POSITIVE LOGITS
    >{"
    0.67
    {"
    0.65
    Vidite
    0.43
    ніципалі
    0.38
    astify
    0.38
     consultato
    0.38
     ////
    0.38
    {`
    0.38
    RefNanny
    0.37
    !*\
    0.37
    Activations Density 0.030%

    No Known Activations