© 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. 20-GEMMASCOPE-RES-131K
    11. 3185
    Prev
    Next
    INDEX
    Explanations

    instances of confession or admission of guilt

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

    admitting or confessing actions

    np_acts-logits-general · gemini-2.5-flash-lite

    reported admissions or claims of responsibility for actions, often within quoted or attributed statements.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     pinulongan
    -0.59
     समीक्षाओं
    -0.56
     ब्रेकडाउन
    -0.54
     ProtoMessage
    -0.51
     Италијани
    -0.50
    ніципалі
    -0.49
    تقاوى
    -0.48
     ModelExpression
    -0.47
    exitRule
    -0.45
     Hypothesis
    -0.44
    POSITIVE LOGITS
     betweenstory
    0.57
     snippetHide
    0.45
     intentionally
    0.44
     bragging
    0.40
     pride
    0.39
     openly
    0.39
     sengaja
    0.38
     pratiques
    0.38
     orgull
    0.37
     intentional
    0.37
    Activations Density 0.161%

    No Known Activations