© 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. 38664
    Prev
    Next
    INDEX
    Explanations

    instructions related to food preparation and cooking methods

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

    cooking and programming terms

    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
     оригіналу
    -0.63
     EconPapers
    -0.58
     ब्रेकडाउन
    -0.58
    期刊论文
    -0.52
     Widodo
    -0.50
    verwijspagina
    -0.47
    bàn
    -0.46
    uple
    -0.45
    ぐり
    -0.45
    abah
    -0.45
    POSITIVE LOGITS
     cooled
    0.60
     prepared
    0.54
    ruptedException
    0.50
     vorbere
    0.46
     dried
    0.45
    EndInit
    0.44
     cooked
    0.43
     remaining
    0.43
    XmlAccessorType
    0.43
    SerializedSize
    0.43
    Activations Density 0.017%

    No Known Activations