© 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. 17-GEMMASCOPE-RES-16K
    6. 4977
    Prev
    Next
    INDEX
    Explanations

    indicators of structured data or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.71
    IFICATE
    -0.62
     defStyleAttr
    -0.61
    Открыть
    -0.59
    astify
    -0.58
    достатки
    -0.58
    radura
    -0.57
    ︎
    -0.56
    SystemColors
    -0.56
     ComVisible
    -0.55
    POSITIVE LOGITS
    ↵↵
    0.86
    )";
    
    0.64
    Personensuche
    0.62
    oa̍t
    0.59
     그리고
    0.58
    ↵↵↵
    0.57
     valamint
    0.57
    */)
    0.56
     فريبيس
    0.55
    esModule
    0.55
    Activations Density 0.034%

    No Known Activations