© 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. 41819
    Prev
    Next
    INDEX
    Explanations

    instances of the word "raw" in various contexts

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

    unprocessed materials and data

    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
     berlaku
    -0.34
    ั้ง
    -0.33
     Finally
    -0.33
     conoce
    -0.33
     finally
    -0.33
    jangkau
    -0.32
     soutenu
    -0.31
     mentioned
    -0.31
     conocen
    -0.31
     diría
    -0.30
    POSITIVE LOGITS
     raw
    0.93
     للاسماء
    0.84
    #+#
    0.82
     RAW
    0.82
     resourceCulture
    0.79
    TypedDataSet
    0.78
     Raw
    0.77
    GEBURTSDATUM
    0.76
    AndEndTag
    0.76
    出版年
    0.75
    Activations Density 0.011%

    No Known Activations