© 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. 65887
    Prev
    Next
    INDEX
    Explanations

    references to graphene and its structural properties

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

    graphene-like structures and derivatives

    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
    lock
    -0.35
    tekend
    -0.35
    pulumi
    -0.34
     spesa
    -0.34
    omock
    -0.34
     ajan
    -0.32
    Ска
    -0.32
    providedIn
    -0.32
    hawat
    -0.32
    sugar
    -0.31
    POSITIVE LOGITS
     graphene
    0.75
     sheets
    0.67
    AutoScaleMode
    0.66
     sheet
    0.63
     disambiguazione
    0.60
    LookAnd
    0.56
     Sheet
    0.54
     ErrIntOverflow
    0.54
    
    0.54
     '\\;'
    0.53
    Activations Density 0.015%

    No Known Activations