© 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. 22-GEMMASCOPE-RES-16K
    11. 11306
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming and error handling, specifically in Maven and Apache Tika

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

    Japanese direct object marker "を"

    np_acts-logits-general · gemini-2.0-flash

    書類や証明書

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    })$}
    -0.94
     iſt
    -0.80
    HtmlAttribute
    -0.80
     purpoſe
    -0.78
    서는
    -0.76
    GraphicsUnit
    -0.75
    />";
    -0.75
    )");
    -0.75
    
    -0.74
    $}}
    -0.73
    POSITIVE LOGITS
    를
    0.97
    을
    0.88
     を
    0.85
    を
    0.76
    方を
    0.64
    することを
    0.64
     being
    0.64
    리를
    0.63
     to
    0.62
    体を
    0.62
    Activations Density 0.062%

    No Known Activations