© 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. 21-GEMMASCOPE-RES-16K
    11. 1473
    Prev
    Next
    INDEX
    Explanations

    terms associated with negative impacts or risks in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    clable
    -0.61
    ண்டும்
    -0.56
    UNTAS
    -0.56
     DbType
    -0.55
    tagext
    -0.55
    RRect
    -0.55
    дент
    -0.54
     Générale
    -0.53
    gez
    -0.53
    HasColumnType
    -0.52
    POSITIVE LOGITS
     affected
    2.47
     impacted
    2.11
     Affected
    2.09
    affected
    2.06
    Affected
    1.91
     AFFECT
    1.77
     effected
    1.60
     affect
    1.58
     affects
    1.55
     afectado
    1.53
    Activations Density 0.420%

    No Known Activations