© 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. 19-GEMMASCOPE-RES-16K
    6. 11465
    Prev
    Next
    INDEX
    Explanations

    elements related to technical specifications or coding examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vidite
    -0.85
    --)
    
    -0.69
    offsetof
    -0.69
     endfor
    -0.68
     незавершена
    -0.67
    — 
    -0.67
    %"),
    -0.67
     saites
    -0.67
    )");
    
    -0.67
    出版年
    -0.67
    POSITIVE LOGITS
    ↵↵↵
    1.41
    ↵↵↵↵↵
    1.20
    ↵↵↵↵
    1.19
    ↵↵↵↵↵↵
    1.18
    ↵↵↵↵↵↵↵
    1.12
    ↵↵↵↵↵↵↵↵
    1.09
    ↵↵↵↵↵↵↵↵↵
    1.06
    ↵↵↵↵↵↵↵↵↵↵↵↵
    1.04
    ↵↵↵↵↵↵↵↵↵↵
    1.02
    ↵↵↵↵↵↵↵↵↵↵↵
    1.00
    Activations Density 0.181%

    No Known Activations