© 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. 37699
    Prev
    Next
    INDEX
    Explanations

    references to chemical suppliers or reagents

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

    chemical company names and locations

    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
    
    -0.56
    InitVars
    -0.54
    ंदीखरीदारी
    -0.53
    sizeCache
    -0.53
    contentLoaded
    -0.52
    EndContext
    -0.52
     kanton
    -0.51
     nonUne
    -0.50
     HasFactory
    -0.50
     calendriers
    -0.49
    POSITIVE LOGITS
     BASF
    0.57
    ścio
    0.40
    BAS
    0.35
    nak
    0.35
     Bap
    0.35
     Baton
    0.34
     Vinc
    0.33
    nehmer
    0.33
    atz
    0.33
    ustin
    0.32
    Activations Density 0.003%

    No Known Activations