© 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. 23-GEMMASCOPE-RES-16K
    11. 6133
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming or code structures in software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enderror
    -0.55
    ReusableCell
    -0.55
    withIdentifier
    -0.54
     chất
    -0.53
    SourceChecksum
    -0.53
    Produzione
    -0.53
    IsMutable
    -0.51
    Notae
    -0.51
     himo
    -0.51
    ยว
    -0.49
    POSITIVE LOGITS
     coordinates
    0.94
     CGPoint
    0.83
     getPosition
    0.83
     coords
    0.82
     position
    0.79
     Coordinates
    0.76
     getLocation
    0.74
     Position
    0.74
     positions
    0.73
     location
    0.70
    Activations Density 0.248%

    No Known Activations