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

    Neuronpedia

    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. 2443
    Prev
    Next
    INDEX
    Explanations

    actions or events associated with movement and location within a campus setting

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

    spatial descriptions or location-based phrases using prepositions like "on," "in," and "of."

    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
    mailto
    -0.28
    ெ
    -0.28
     Pan
    -0.27
    baren
    -0.27
     Konf
    -0.27
    eqn
    -0.26
     Wein
    -0.26
     Box
    -0.25
     Black
    -0.25
    <!--[
    -0.25
    POSITIVE LOGITS
     campus
    1.68
     premises
    1.42
    campus
    1.34
     onsite
    1.27
    敷地
    1.25
     campuses
    1.23
    Campus
    1.20
     grounds
    1.19
     CAMPUS
    1.17
     Campus
    1.15
    Activations Density 0.243%

    No Known Activations