© 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. 20-GEMMASCOPE-RES-16K
    6. 10616
    Prev
    Next
    INDEX
    Explanations

    JavaScript-related function definitions and method calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code that retrieves data by ID

    np_acts-logits-general · gemini-2.0-flash

    get by id or name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsContent
    -0.61
    httphttps
    -0.59
    Tikang
    -0.58
    Jeografia
    -0.54
     виправивши
    -0.48
    EnableWeb
    -0.48
    expandindo
    -0.47
    AppRoutingModule
    -0.47
    AddComponent
    -0.46
    addAll
    -0.46
    POSITIVE LOGITS
    ById
    1.14
    ByID
    1.00
    ByPrimaryKey
    0.94
    findById
    0.93
     findById
    0.92
    byId
    0.91
     by
    0.88
    ViewById
    0.82
     getById
    0.82
     findOne
    0.76
    Activations Density 0.186%

    No Known Activations