© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 94160
    Prev
    Next
    INDEX
    Explanations

    references to personal appearance and self-assessment

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

    for your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nonUne
    -0.44
    Espèce
    -0.41
    ysaccharide
    -0.35
     nargin
    -0.35
     usług
    -0.35
     usługi
    -0.35
     beschikbaar
    -0.35
    readObject
    -0.33
    issau
    -0.33
    MLLoader
    -0.32
    POSITIVE LOGITS
    Diweddarwch
    0.55
     styl
    0.46
     flattering
    0.44
    applique
    0.43
     Boch
    0.42
    ftagPool
    0.42
     styles
    0.42
     betweenstory
    0.42
    Παραπομπές
    0.41
    WebControls
    0.41
    Activations Density 0.005%

    No Known Activations