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

    Neuronpedia

    Jacobian LensNEW
    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. 8827
    Prev
    Next
    INDEX
    Explanations

    discussions related to legal and procedural nuances, including claims and sentencing

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

    References or citations (e.g., see, refer to)

    np_acts-logits-general · gemini-2.0-flash

    referring to see

    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
    XMLSchema
    -0.67
    enterOuterAlt
    -0.66
    +#+#
    -0.61
    endphp
    -0.58
     utafitiHapana
    -0.57
    InjectAttribute
    -0.56
    SequentialGroup
    -0.55
     @"/
    -0.53
    новништво
    -0.52
    Demografía
    -0.51
    POSITIVE LOGITS
     see
    3.01
     See
    2.66
    see
    2.63
    See
    2.61
     siehe
    2.03
     SEE
    1.93
     Siehe
    1.92
     sees
    1.78
     voir
    1.74
    SEE
    1.70
    Activations Density 1.982%

    No Known Activations