© 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. 2-GEMMASCOPE-RES-16K
    11. 3513
    Prev
    Next
    INDEX
    Explanations

    mentions of columns or column-related concepts in the context of data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.89
    ngdoc
    -0.71
    Jereo
    -0.71
     simplifié
    -0.69
    makeConstraints
    -0.69
    */),
    -0.67
    "])
    -0.66
     Réponses
    -0.66
    )");
    -0.65
    ształ
    -0.64
    POSITIVE LOGITS
    col
    3.06
     Col
    2.93
    Col
    2.90
     col
    2.81
     COL
    2.33
    COL
    2.29
     cols
    1.83
    Cols
    1.79
    cols
    1.64
     Kol
    1.61
    Activations Density 0.060%

    No Known Activations