© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 81265
    Prev
    Next
    INDEX
    Explanations

    references to product offerings and related terminology

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

    offerings

    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
     Comprometido
    -0.47
    astéro
    -0.43
     Савезне
    -0.41
     abscess
    -0.39
    Étape
    -0.39
     validés
    -0.39
    認証
    -0.38
     JADX
    -0.38
    éfono
    -0.37
     bestätigen
    -0.37
    POSITIVE LOGITS
     offerings
    1.09
     Offerings
    0.98
    Offered
    0.97
     offered
    0.96
    Offer
    0.95
    offered
    0.95
    offering
    0.94
     Offer
    0.94
    offerta
    0.94
     offering
    0.93
    Activations Density 0.012%

    No Known Activations