© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5649
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to access modifiers and static definitions in source code

    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
    finally
    -0.45
     toward
    -0.43
    would
    -0.43
    towards
    -0.42
     Jara
    -0.42
     finally
    -0.41
    FINALLY
    -0.41
     towards
    -0.41
    whatever
    -0.40
     FINALLY
    -0.40
    POSITIVE LOGITS
     boolean
    1.14
     bool
    1.01
    boolean
    1.00
     int
    0.89
    bool
    0.86
     float
    0.73
    int
    0.72
     String
    0.71
    Datuak
    0.60
     string
    0.59
    Activations Density 0.224%

    No Known Activations