© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 9505
    Prev
    Next
    INDEX
    Explanations

    specific roles and professions, particularly those relating to the arts and sciences

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

    professional titles and occupations in written content.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    professional titles and occupational roles.

    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
    tagHelperRunner
    -0.44
     seguido
    -0.36
     mariscos
    -0.35
     verdaderos
    -0.33
     verdaderas
    -0.33
     truly
    -0.33
     aislada
    -0.33
    ┼
    -0.32
     hängt
    -0.31
     verdadero
    -0.31
    POSITIVE LOGITS
    ſelf
    0.73
     Chwiliwch
    0.70
    們
    0.64
    Хьажоргаш
    0.62
     Wikimedijinoj
    0.62
     ſche
    0.61
     Eſ
    0.61
    soort
    0.61
     ſch
    0.60
     ModelExpression
    0.59
    Activations Density 0.634%

    No Known Activations