© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 95978
    Prev
    Next
    INDEX
    Explanations

    contexts involving suspicion or the act of suspecting someone or something

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

    suspect/suspected that

    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
     gjerne
    -0.46
     nôtre
    -0.45
    kjø
    -0.44
    ürm
    -0.44
     océ
    -0.44
    livre
    -0.43
     tilbud
    -0.42
    面的
    -0.42
     Ganzen
    -0.42
     hôtel
    -0.42
    POSITIVE LOGITS
     suspect
    0.90
     suspicion
    0.85
     suspected
    0.75
     suspicions
    0.73
    picion
    0.65
     vermute
    0.61
     sospe
    0.60
     suspects
    0.60
     suspicious
    0.57
     expect
    0.56
    Activations Density 0.011%

    No Known Activations