© 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. 21-GEMMASCOPE-RES-16K
    11. 12330
    Prev
    Next
    INDEX
    Explanations

    HTML style attributes and their settings

    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
    IVEREF
    -0.60
     RIPRODUZIONE
    -0.59
     Theſe
    -0.58
     Réalisation
    -0.56
    Välislingid
    -0.55
    DropTable
    -0.54
     flèche
    -0.53
    Cevap
    -0.52
     odkazy
    -0.52
     ObjectParameter
    -0.52
    POSITIVE LOGITS
    ={{
    0.58
     MessageBoxIcon
    0.51
    zzleHttp
    0.50
    didSet
    0.50
    WebElementEntity
    0.50
    UrlResolution
    0.49
     TextStyle
    0.48
    tifiable
    0.47
    AutoScale
    0.46
    Slf
    0.46
    Activations Density 0.039%

    No Known Activations