© 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-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 15582
    Prev
    Next
    INDEX
    Explanations

    HTML and UI component elements within code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ga
    -0.46
     Nor
    -0.43
    bero
    -0.40
     root
    -0.40
    fatta
    -0.39
    每
    -0.39
    joit
    -0.39
     déri
    -0.38
    PLING
    -0.37
    oured
    -0.37
    POSITIVE LOGITS
    CardContent
    0.94
    MLLoader
    0.91
    ImageContext
    0.90
     ExecuteAsync
    0.89
    Tembelea
    0.87
    CardBody
    0.86
    posedge
    0.83
    ChildScrollView
    0.83
    PerformLayout
    0.77
    kháu
    0.76
    Activations Density 0.046%

    No Known Activations