© 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. 7-GEMMASCOPE-RES-16K
    11. 8560
    Prev
    Next
    INDEX
    Explanations

    words related to capturing and visual representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pat
    -0.73
     отношению
    -0.61
      
    -0.59
     menga
    -0.58
    Esk
    -0.57
    d
    -0.57
     d
    -0.56
     to
    -0.56
     W
    -0.55
     m
    -0.54
    POSITIVE LOGITS
     Capture
    1.66
     captures
    1.60
     capture
    1.54
    capture
    1.44
     captured
    1.42
    Capture
    1.42
     capturing
    1.40
    captures
    1.37
    captured
    1.31
     captur
    1.30
    Activations Density 0.101%

    No Known Activations