© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 21723
    Prev
    Next
    INDEX
    Explanations

    concepts related to boundaries and divisions, especially in social contexts

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

    between entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     confronti
    -0.36
    ▾
    -0.31
     négociations
    -0.30
     alguna
    -0.30
    Others
    -0.29
     oiseaux
    -0.29
     אחת
    -0.28
     либо
    -0.28
     algún
    -0.28
    sweetalert
    -0.28
    POSITIVE LOGITS
     sexes
    1.26
     genres
    1.10
     worlds
    1.09
     genders
    1.09
     cultures
    1.09
     factions
    1.02
     hemispheres
    1.00
     different
    0.90
     castes
    0.90
    兩種
    0.88
    Activations Density 0.258%

    No Known Activations