© 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. 10-GEMMASCOPE-RES-16K
    6. 6393
    Prev
    Next
    INDEX
    Explanations

    symbols and notations related to mathematical expressions or equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IBOutlet
    -0.71
    ctest
    -0.68
    onDestroy
    -0.67
     Bento
    -0.65
    Välislingid
    -0.63
     aio
    -0.62
    Tikang
    -0.61
    ValueStyle
    -0.61
     Artifact
    -0.60
     Mato
    -0.60
    POSITIVE LOGITS
     $\
    1.36
    $\
    1.06
    {$\
    0.80
     $(\
    0.79
     \
    0.73
     ($\
    0.70
     {$\
    0.65
     $\{\
    0.63
     "\
    0.61
    }{$\
    0.60
    Activations Density 0.319%

    No Known Activations