© 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-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 4917
    Prev
    Next
    INDEX
    Explanations

    elements related to image processing and manipulation in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.44
    Moth
    -0.33
    VYMaps
    -0.33
     صوتيه
    -0.32
    ytä
    -0.32
    Vpc
    -0.32
     henna
    -0.31
     salvación
    -0.30
     permitirá
    -0.30
     graphique
    -0.30
    POSITIVE LOGITS
    ValueStyle
    0.60
     nakalista
    0.57
    GOTREF
    0.53
    setVerticalGroup
    0.52
    astify
    0.50
    MessageOf
    0.49
    日閲覧
    0.48
     ModelExpression
    0.48
    
    0.47
    endela
    0.47
    Activations Density 0.548%

    No Known Activations