© 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. 31-GEMMASCOPE-RES-131K
    11. 37482
    Prev
    Next
    INDEX
    Explanations

    concepts related to deception and appearances

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

    deceiving or being misled

    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
     Италијани
    -0.56
    SharedCtor
    -0.50
     externi
    -0.45
    rungsseite
    -0.43
    UnknownFieldSet
    -0.40
    Parcelize
    -0.39
    surate
    -0.38
    Cyfarwyddwr
    -0.38
     Numerade
    -0.38
    WireFormat
    -0.38
    POSITIVE LOGITS
     deceiving
    1.63
     deceptive
    1.52
     deceive
    1.52
     deception
    1.49
     deceived
    1.47
     misleading
    1.47
     fooled
    1.45
     mislead
    1.35
     misled
    1.23
     tricked
    1.23
    Activations Density 0.095%

    No Known Activations