© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 6180
    Prev
    Next
    INDEX
    Explanations

    references to code imports and wiki links

    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
    клопе
    -0.78
    ulipas
    -0.74
    Grüße
    -0.68
     estudian
    -0.67
     '@/
    -0.63
     Serbie
    -0.63
     faſt
    -0.62
    ✨:
    -0.61
     neceff
    -0.61
     město
    -0.60
    POSITIVE LOGITS
     مشين
    0.86
    ArgsConstructor
    0.70
    ReusableCell
    0.67
     Dostupné
    0.57
    IMPORTED
    0.55
    TagMode
    0.55
    KommentareTeilen
    0.55
     الرخصة
    0.54
    CDATA
    0.54
    StackNavigator
    0.54
    Activations Density 0.014%

    No Known Activations