© 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. 10-GEMMASCOPE-RES-16K
    11. 15427
    Prev
    Next
    INDEX
    Explanations

    key figures and concepts related to political and social power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Signalez
    -1.18
     مرئيه
    -1.01
    parsedMessage
    -0.96
     lenker
    -0.92
    Билгалдахарш
    -0.91
    Искәрмәләр
    -0.91
     Paglinawan
    -0.91
    expandindo
    -0.89
    رشف
    -0.84
     disambiguazione
    -0.84
    POSITIVE LOGITS
    ↵↵
    0.54
     such
    0.54
    .
    0.46
    hasOwnProperty
    0.46
    onNext
    0.42
    Such
    0.42
    isHidden
    0.41
    roy
    0.41
    idian
    0.39
     situation
    0.39
    Activations Density 0.704%

    No Known Activations