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

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-131K
    11. 40237
    Prev
    Next
    INDEX
    Explanations

    expressions of honesty and confessions

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

    admitting or confessing

    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
     surla
    -0.76
    ArgsConstructor
    -0.70
    RotationOrder
    -0.57
    ########.
    -0.55
    InputBorder
    -0.55
     للمعارف
    -0.53
    PMailer
    -0.52
    exitRule
    -0.52
    قایناق‌لار
    -0.52
     الحره
    -0.51
    POSITIVE LOGITS
     admit
    0.64
     admitted
    0.59
     Admit
    0.56
    正直
    0.55
     admits
    0.52
     confess
    0.51
     confessed
    0.50
     frankly
    0.49
     admitting
    0.48
    honestly
    0.47
    Activations Density 0.059%

    No Known Activations