© 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. 31-GEMMASCOPE-RES-131K
    11. 65534
    Prev
    Next
    INDEX
    Explanations

    phrases related to deception or misrepresentation

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

    disguised disguise masked guise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Patrimonio
    -0.36
     tirantes
    -0.34
    componentWill
    -0.34
     Cadena
    -0.32
     vivas
    -0.31
    wiki
    -0.30
     compter
    -0.30
     Streifen
    -0.30
     huelga
    -0.29
    ęki
    -0.29
    POSITIVE LOGITS
     disguised
    2.05
     disguise
    1.87
     masquer
    1.64
     disgu
    1.59
     disfraz
    1.43
     masked
    1.30
     dressed
    1.29
     masquerade
    1.25
     guise
    1.24
    guise
    1.17
    Activations Density 0.121%

    No Known Activations