© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104504
    Prev
    Next
    INDEX
    Explanations

    code related to object properties and descriptors in JavaScript

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.81
    aarrggbb
    -0.74
    RenderAtEndOf
    -0.72
    EndInit
    -0.70
    IBOutlet
    -0.70
    SourceChecksum
    -0.68
    ########.
    -0.68
    URLException
    -0.66
    endpush
    -0.64
     مرئيه
    -0.64
    POSITIVE LOGITS
     clock
    0.35
    大
    0.33
    被
    0.32
     
    0.31
     fiind
    0.30
    extrême
    0.29
      
    0.28
    clock
    0.28
     fair
    0.28
    Prop
    0.28
    Activations Density 0.021%

    No Known Activations