© 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. 18-GEMMASCOPE-RES-16K
    11. 341
    Prev
    Next
    INDEX
    Explanations

    numerical data representations or numeric patterns

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

    Numbers following "0" or a period

    np_acts-logits-general · gemini-2.0-flash

    mathematical or scientific context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <i>
    -0.62
    endmodule
    -0.61
    ↵↵↵
    -0.59
    ↵↵↵↵↵
    -0.57
    rande
    -0.56
    -0.56
     مُعرِّف
    -0.56
     DbType
    -0.56
     Samo
    -0.55
    urka
    -0.55
    POSITIVE LOGITS
    getKeyCode
    1.02
    0
    0.99
    AndEndTag
    0.82
     kaynağından
    0.79
    তথ্যসূত্র
    0.79
     Tors
    0.79
    yntaxException
    0.76
     Commandments
    0.75
     Tencent
    0.74
     Fas
    0.74
    Activations Density 0.316%

    No Known Activations