© 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. 12069
    Prev
    Next
    INDEX
    Explanations

    instances of hypocrisy and related contradictory behavior

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

    talking and pronouncements

    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
    本線
    -0.36
    存于互联网档案馆
    -0.36
     transfieras
    -0.36
     Wiktionnaire
    -0.35
    ScopeManager
    -0.34
    ctools
    -0.33
    DateTimePicker
    -0.33
    SuppressLint
    -0.33
    zulegen
    -0.33
    TemporalType
    -0.33
    POSITIVE LOGITS
     talk
    1.48
     rhetoric
    1.24
    talk
    1.20
     TALK
    1.16
     Talk
    1.15
     words
    1.14
    Talk
    1.09
     lip
    1.05
     talked
    1.00
     promises
    0.98
    Activations Density 0.166%

    No Known Activations