Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6655
    Prev
    Next
    INDEX
    Explanations

    code-related syntax elements and structure in programming documentation

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

    Code, categories, and references

    np_acts-logits-general · gemini-2.0-flash

    documentation and code

    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
     myſelf
    -0.72
     poffe
    -0.71
     Eſ
    -0.70
     faſt
    -0.69
     Efq
    -0.69
     itſelf
    -0.67
     Jefus
    -0.66
     }}$}
    -0.66
    ientôt
    -0.66
     
    -0.64
    POSITIVE LOGITS
    <b>
    1.48
    </b>
    1.08
    /*
    1.05
    </i>
    1.03
     /*
    0.93
    dfrac
    0.92
    <i>
    0.90
    /*
    
    0.66
     ${\
    0.64
    例文帳に追加
    0.62
    Activations Density 0.171%

    No Known Activations