© 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. 202
    Prev
    Next
    INDEX
    Explanations

    descriptions of skills and capabilities

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

    describing skill or ability

    np_acts-logits-general · gemini-2.0-flash

    skill or quality followed by at

    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
    ReusableCell
    -0.62
    ThroughAttribute
    -0.60
     مشين
    -0.56
     sumpay
    -0.55
    tryk
    -0.53
    """.
    -0.53
    addContainerGap
    -0.50
    ContentAsync
    -0.49
    </tfoot>
    -0.48
     ostavi
    -0.46
    POSITIVE LOGITS
     at
    1.00
     adept
    0.77
     excels
    0.76
     excel
    0.73
    擅长
    0.72
     proficient
    0.69
     excelled
    0.67
     darin
    0.65
     Normdatei
    0.65
     nisso
    0.64
    Activations Density 0.139%

    No Known Activations