© 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. 8-GEMMASCOPE-RES-16K
    11. 8314
    Prev
    Next
    INDEX
    Explanations

    structured data formats, particularly related to metadata and JSON-like structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     كومونز
    -0.96
    )");
    -0.93
    )";
    -0.89
    ']))
    -0.87
    >");
    -0.81
    `;
    -0.79
     FetchType
    -0.78
    клопе
    -0.77
     ChromeDriver
    -0.76
     kaynağından
    -0.75
    POSITIVE LOGITS
     
    0.46
     opie
    0.42
    ->
    0.40
      
    0.40
    ↵
    0.40
    type
    0.39
    楼主
    0.38
    ните
    0.38
     baja
    0.37
     type
    0.37
    Activations Density 0.776%

    No Known Activations