© 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. 5591
    Prev
    Next
    INDEX
    Explanations

    terms related to mechanics and problem-solving in a technical context

    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
     CascadeType
    -0.35
    SequentialGroup
    -0.35
    ActionCreators
    -0.33
    CascadeType
    -0.33
     Wikispecies
    -0.32
    argout
    -0.30
    wness
    -0.29
     attribution
    -0.29
     zespół
    -0.29
    Mediabestanden
    -0.28
    POSITIVE LOGITS
     stairs
    0.91
     platforms
    0.86
     Platforms
    0.81
     platform
    0.79
     doors
    0.78
     floors
    0.78
     chests
    0.76
     ledges
    0.75
     ledge
    0.75
     floor
    0.75
    Activations Density 0.239%

    No Known Activations