© 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. 111724
    Prev
    Next
    INDEX
    Explanations

    references to specific artists and scientific terminology related to biochemical processes

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

    fatty acid, biotin, and CoA metabolism

    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
     <=",
    -0.52
    الحياه
    -0.48
    IVEREF
    -0.40
    haikusbot
    -0.39
     Valera
    -0.39
    Dry
    -0.38
    writeField
    -0.38
    ніципалі
    -0.37
    inerja
    -0.35
    Mustang
    -0.35
    POSITIVE LOGITS
     Rihanna
    0.82
    Rihanna
    0.78
     Barbados
    0.78
     Barba
    0.65
    Barbados
    0.64
     Caribbean
    0.61
    Caribbean
    0.50
     Baj
    0.47
     island
    0.44
     caribbean
    0.44
    Activations Density 0.003%

    No Known Activations