© 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. 31-GEMMASCOPE-RES-131K
    11. 5205
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and expressions of personal experience or perspective

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

    I speaking about oneself

    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
     NavController
    -0.55
     pouvoit
    -0.54
     MessageBoxIcon
    -0.53
    ientras
    -0.51
     dieux
    -0.50
    Jereo
    -0.49
     biß
    -0.49
    HomeAsUpEnabled
    -0.49
    と思ったら
    -0.48
    ñores
    -0.47
    POSITIVE LOGITS
     Particularly
    0.56
     particularly
    0.52
     особенно
    0.44
     particularmente
    0.42
    Often
    0.42
    particularly
    0.41
    собенно
    0.41
     Besonders
    0.41
    ticularly
    0.41
    Interested
    0.41
    Activations Density 0.065%

    No Known Activations