© 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. 37-GEMMASCOPE-RES-16K
    11. 4036
    Prev
    Next
    INDEX
    Explanations

    symbols and characters related to technical commands or programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.48
    /*
    -0.35
    jsxFileName
    -0.35
     ligiloj
    -0.34
     flash
    -0.34
     atlas
    -0.33
    pula
    -0.33
    Flash
    -0.33
     rad
    -0.33
    flash
    -0.33
    POSITIVE LOGITS
    RectangleBorder
    0.56
    Бахар
    0.54
    InSection
    0.53
    ReusableCell
    0.50
    SequentialGroup
    0.49
    ftagPool
    0.47
     Taktlose
    0.44
     convertView
    0.44
    RegressionTest
    0.42
    CppMethod
    0.42
    Activations Density 1.031%

    No Known Activations