© 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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 28238
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically commas and periods

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

    list item separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     entanto
    -0.75
    aData
    -0.71
    prav
    -0.67
    Viitteet
    -0.66
    bestand
    -0.66
     Furman
    -0.66
     Fot
    -0.66
    likle
    -0.66
    ajur
    -0.66
    𝐱
    -0.66
    POSITIVE LOGITS
     Walpole
    0.98
    )",
    0.94
    ",
    0.93
    '",
    0.92
    %",
    0.84
    ]",
    0.82
    )".
    0.82
    </th>
    0.80
    }}{
    0.79
    \"",
    0.79
    Activations Density 0.059%

    No Known Activations