© 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. 11-GEMMASCOPE-RES-16K
    6. 4461
    Prev
    Next
    INDEX
    Explanations

    references to relationships or relations within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]--;
    -1.03
    脚注の使い方
    -1.03
    -------------</
    -1.03
    ceutical
    -0.95
    SourceChecksum
    -0.95
    argout
    -0.94
    andescent
    -0.93
    +#+#
    -0.93
     webdriver
    -0.92
    adecimal
    -0.91
    POSITIVE LOGITS
    rs
    0.83
    Gr
    0.81
    on
    0.80
     gr
    0.79
    ins
    0.73
    r
    0.71
    l
    0.71
    del
    0.69
    en
    0.69
    ars
    0.69
    Activations Density 0.185%

    No Known Activations