© 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. 20-GEMMASCOPE-RES-16K
    11. 12007
    Prev
    Next
    INDEX
    Explanations

    numerical references, including figures and tables

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

    figures or tables

    np_acts-logits-general · gemini-2.0-flash

    Figures and tables citations

    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
     correctes
    -0.67
    出版年
    -0.63
     createSlice
    -0.62
    ConstraintMaker
    -0.62
     getItemCount
    -0.60
    #!/
    -0.58
     precisely
    -0.57
    awakeFromNib
    -0.55
    SuspendLayout
    -0.54
    UnknownFields
    -0.54
    POSITIVE LOGITS
    setof
    0.58
     nawr
    0.56
    UserScript
    0.55
    fastjson
    0.52
    ErrorException
    0.50
     informée
    0.49
    )”.
    0.49
    `"
    0.48
     مرئيه
    0.47
     typelib
    0.47
    Activations Density 0.769%

    No Known Activations