© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 15096
    Prev
    Next
    INDEX
    Explanations

    words associated with events, interactions, and actions occurring in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sequences describing movement or action verbs in the context of going in and out of spaces or locations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Abitanti
    -0.41
    ötzlich
    -0.34
    ěry
    -0.33
    ikala
    -0.32
     يتيمه
    -0.30
     tacón
    -0.30
    ępo
    -0.29
    ViewImports
    -0.29
    ichtet
    -0.29
    Населення
    -0.29
    POSITIVE LOGITS
     outside
    2.66
     Outside
    2.42
    outside
    2.39
    Outside
    2.33
     external
    2.31
     exterior
    2.27
     outdoors
    2.25
     OUTSIDE
    2.20
    OUTSIDE
    2.08
     outdoor
    2.06
    Activations Density 0.562%

    No Known Activations