© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 9101
    Prev
    Next
    INDEX
    Explanations

    topics related to research methodologies and experimental testing in scientific contexts

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

    followed by prepositions or question marks

    np_acts-logits-general · gemini-2.0-flash

    analysis and descriptions

    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
     IndexPath
    -0.79
     تضيفلها
    -0.77
    PostExecute
    -0.74
     كومونز
    -0.73
    tvguidetime
    -0.70
    Véxase
    -0.69
    providedIn
    -0.69
    }-*/;
    -0.68
    Datuak
    -0.67
    uxxxx
    -0.67
    POSITIVE LOGITS
    </h2>
    1.04
    </h3>
    0.98
    ↵↵
    0.93
    </h4>
    0.86
    </h1>
    0.73
    ?
    0.70
    </h5>
    0.70
    <tbody>
    0.64
    ↵
    0.59
    0.55
    Activations Density 0.463%
    No Known Activations