© 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. 10636
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to specific individuals or roles 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 @ 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
    комму
    -0.99
    IndentedString
    -0.90
    contentLoaded
    -0.89
    Tikang
    -0.88
    }))
    -0.75
    ulemon
    -0.73
    ogeneity
    -0.73
    RTDA
    -0.72
    __;
    -0.71
     برانيه
    -0.69
    POSITIVE LOGITS
    ar
    0.99
     Karin
    0.98
    AR
    0.93
    arn
    0.92
     Kars
    0.89
    ARL
    0.87
    arne
    0.87
    arin
    0.87
    lar
    0.86
    aric
    0.86
    Activations Density 0.684%

    No Known Activations