© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4622
    Prev
    Next
    INDEX
    Explanations

    references to documentation or data sets

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

    ending in "table", "ation", or "ing"

    np_acts-logits-general · gemini-2.0-flash

    documentation and reporting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebControls
    -0.73
    Tikang
    -0.68
    t
    -0.60
    PMailer
    -0.55
    tory
    -0.54
     مرئيه
    -0.54
    protoimpl
    -0.53
    miche
    -0.53
    lioma
    -0.50
     resourceCulture
    -0.50
    POSITIVE LOGITS
    table
    0.55
    thouse
    0.50
    embolso
    0.48
    routeProvider
    0.47
    ьаж
    0.47
     وتسجيلات
    0.47
    tability
    0.47
    tables
    0.47
    tably
    0.45
    thard
    0.45
    Activations Density 0.234%

    No Known Activations