© 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. 3981
    Prev
    Next
    INDEX
    Explanations

    code structure and annotations related to data modeling

    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
     reflejo
    -0.42
    queryset
    -0.41
     fiabilidad
    -0.40
     hasilnya
    -0.40
     warunk
    -0.40
    Viki
    -0.39
    TestingModule
    -0.39
    braucher
    -0.39
     gericht
    -0.39
    tető
    -0.37
    POSITIVE LOGITS
    protected
    0.72
    readonly
    0.68
    public
    0.67
    private
    0.63
     protected
    0.62
     public
    0.59
     readonly
    0.59
     private
    0.57
    ItemBackground
    0.47
     Protected
    0.46
    Activations Density 0.356%

    No Known Activations