© 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. 9-GEMMASCOPE-RES-131K
    6. 76751
    Prev
    Next
    INDEX
    Explanations

    words related to suspicion and doubt

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

    suspicious or questionable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ThemeData
    -0.53
    ########.
    -0.46
    UrlResolution
    -0.46
    breite
    -0.45
     Majefty
    -0.43
     Suivez
    -0.43
     leia
    -0.43
    Slf
    -0.42
     îna
    -0.42
     âmes
    -0.41
    POSITIVE LOGITS
     suspicious
    1.86
    Suspicious
    1.57
    picious
    1.50
     suspiciously
    1.13
     suspicions
    1.02
     suspicion
    1.01
    sus
    0.92
     suspic
    0.90
     Sus
    0.86
     Mysterious
    0.81
    Activations Density 0.003%

    No Known Activations