© 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. 14608
    Prev
    Next
    INDEX
    Explanations

    references to non-entities or non-parameters in various contexts

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

    negation prefix

    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
    ScopeManager
    -0.74
     Erwä
    -0.56
    tagHelper
    -0.54
    fjspx
    -0.53
    ingway
    -0.53
     îna
    -0.52
     HasFactory
    -0.52
     Zeitpunkt
    -0.52
     bookId
    -0.50
     courseId
    -0.50
    POSITIVE LOGITS
     non
    1.35
     Non
    1.35
    Non
    1.21
    non
    1.13
     NON
    1.08
    NON
    0.95
     nons
    0.82
     Nons
    0.82
    非
    0.81
     非
    0.75
    Activations Density 0.062%

    No Known Activations