© 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. 0-GEMMASCOPE-RES-16K
    11. 7863
    Prev
    Next
    INDEX
    Explanations

    patterns related to the function pointer in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.10
     myſelf
    -1.00
     Monfieur
    -0.91
     Majefty
    -0.91
     fevere
    -0.90
     Theſe
    -0.90
     Jefus
    -0.89
     uſed
    -0.89
     auffi
    -0.85
     purpoſe
    -0.85
    POSITIVE LOGITS
    StoryboardSegue
    0.97
     Kin
    0.81
    </caption>
    0.73
     key
    0.73
     along
    0.71
     kin
    0.70
    aarrggbb
    0.68
    Tikang
    0.66
    AnchorStyles
    0.66
    ViewFeatures
    0.65
    Activations Density 0.143%

    No Known Activations