© 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 EvalsExportsinterp-engineNEWAPI 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. 2621
    Prev
    Next
    INDEX
    Explanations

    references to procedures or methods related to file handling and data processing

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

    directly or straight

    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
    illus
    -0.36
     resourceCulture
    -0.35
    EnumValue
    -0.34
    dummy
    -0.33
     partial
    -0.31
    aku
    -0.31
    Галерея
    -0.31
    льність
    -0.31
     compensation
    -0.31
    łę
    -0.31
    POSITIVE LOGITS
     directly
    2.75
    directly
    2.61
     direct
    2.59
     Directly
    2.50
    直接
    2.44
     directement
    2.42
     directamente
    2.39
    direct
    2.36
    Direct
    2.31
     diretamente
    2.30
    Activations Density 0.473%

    No Known Activations