© 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. 37655
    Prev
    Next
    INDEX
    Explanations

    occurrences of the pronoun "I" and its variations

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

    I or we state preference/action

    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
    RectangleBorder
    -0.50
    SourceChecksum
    -0.49
    IRQn
    -0.41
     MainAxisSize
    -0.36
     становника
    -0.35
    uestamente
    -0.35
     seemingly
    -0.32
     Mitarbeit
    -0.32
     aparentemente
    -0.31
     Winaray
    -0.31
    POSITIVE LOGITS
     prefers
    1.05
     prefer
    1.02
    Prefer
    0.93
     предпочита
    0.92
     Prefer
    0.92
    prefer
    0.85
     preferring
    0.79
     recommend
    0.78
     recommends
    0.78
     preferred
    0.77
    Activations Density 0.041%

    No Known Activations