© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 11462
    Prev
    Next
    INDEX
    Explanations

    references to code documentation and structure

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

    file paths and code

    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
    ch
    -0.35
    ↵
    -0.35
    ↵↵
    -0.33
     
    -0.33
    <
    -0.33
    2
    -0.32
    h
    -0.31
    "
    -0.31
    hi
    -0.30
    ,
    -0.30
    POSITIVE LOGITS
    +#+#
    1.04
     nahilalakip
    0.99
     CreateTagHelper
    0.98
    httphttps
    0.95
     ویکی‌پدی
    0.95
    AddTagHelper
    0.94
     pinulongan
    0.91
     informée
    0.90
     kasarigan
    0.89
    expandindo
    0.89
    Activations Density 0.000%

    No Known Activations