© 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. 37-GEMMASCOPE-RES-16K
    6. 4370
    Prev
    Next
    INDEX
    Explanations

    instances of volunteer contributions or donations

    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
    /**
    -0.60
    EReference
    -0.50
     AssemblyTitle
    -0.46
    MessageOf
    -0.40
    MigrationBuilder
    -0.40
     magari
    -0.37
    QMetaType
    -0.37
    BaseAdapter
    -0.36
     Between
    -0.36
    Between
    -0.36
    POSITIVE LOGITS
     nearly
    2.42
    nearly
    2.09
     almost
    2.06
     Nearly
    1.96
    Nearly
    1.93
     hampir
    1.77
     quase
    1.77
    Almost
    1.74
     Almost
    1.73
    almost
    1.69
    Activations Density 0.625%

    No Known Activations