© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 84107
    Prev
    Next
    INDEX
    Explanations

    terms related to direct connections, direct effects, and direct access in various contexts

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

    direct effects and relationships

    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
    seamnă
    -0.49
    tagHelperRunner
    -0.38
     McL
    -0.30
    ؤلاء
    -0.30
    ⓘ
    -0.30
    anky
    -0.29
    хь
    -0.28
    UserEntity
    -0.28
     Rä
    -0.27
     Warenkorb
    -0.27
    POSITIVE LOGITS
    Direct
    1.02
     Direct
    0.96
    direct
    0.90
    Indirect
    0.89
     Indirect
    0.86
     direct
    0.84
     DIRECT
    0.78
    indirect
    0.77
     indirect
    0.74
    DIRECT
    0.73
    Activations Density 0.019%

    No Known Activations