© 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. 4-GEMMASCOPE-RES-16K
    11. 10704
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to editing, changing, and managing configurations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VersionUID
    -0.66
    errHandler
    -0.54
    Према
    -0.54
    jTable
    -0.53
    getRuntime
    -0.52
    Vaya
    -0.50
    Демографія
    -0.49
     SPIE
    -0.49
    ToFit
    -0.49
    })),
    -0.48
    POSITIVE LOGITS
    AutoresizingMask
    0.74
    WebElementEntity
    0.64
    InputTagHelper
    0.59
    Jeografia
    0.58
     iprot
    0.57
    aarrggbb
    0.57
    ciutto
    0.57
     segredo
    0.56
    Mysterious
    0.55
    ThroughAttribute
    0.55
    Activations Density 0.984%

    No Known Activations