© 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. 7-GEMMASCOPE-RES-16K
    11. 9231
    Prev
    Next
    INDEX
    Explanations

    names of specific biological and chemical substances or processes related to health and medicine

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.97
     quæ
    -0.91
    Datuak
    -0.89
     विश्वसनीयता
    -0.83
    ConstraintMaker
    -0.83
     greateſt
    -0.82
    apimachinery
    -0.82
    IUrlHelper
    -0.82
    újo
    -0.82
    größ
    -0.82
    POSITIVE LOGITS
     dig
    0.75
    Demografía
    0.72
     Alpen
    0.66
     digital
    0.64
     сы
    0.60
     Dig
    0.59
     Potter
    0.59
     arts
    0.58
     PIE
    0.57
    fare
    0.57
    Activations Density 2.046%

    No Known Activations