© 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. 25-GEMMASCOPE-RES-16K
    11. 12171
    Prev
    Next
    INDEX
    Explanations

    programming or coding constructs related to data handling and manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nullptr
    -0.73
     nullptr
    -0.71
     constexpr
    -0.67
     https
    -0.66
    cloudfront
    -0.61
     facebook
    -0.60
     Facebook
    -0.60
    facebook
    -0.59
    https
    -0.59
    constexpr
    -0.58
    POSITIVE LOGITS
    0.66
    
    0.63
     muß
    0.55
     mußte
    0.54
     daß
    0.54
    softc
    0.52
     idéia
    0.52
     vax
    0.51
     Xt
    0.50
     cellspacing
    0.50
    Activations Density 0.794%

    No Known Activations