© 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-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 28566
    Prev
    Next
    INDEX
    Explanations

    self-reflective statements and expressions of identity

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

    personal appearance and behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.81
    NUMX
    -0.73
    IntoConstraints
    -0.71
    calaureate
    -0.71
     дописавши
    -0.69
    CloseOperation
    -0.69
    StoryboardSegue
    -0.69
    ]--;
    -0.68
    Hentet
    -0.68
    তথ্যসূত্র
    -0.67
    POSITIVE LOGITS
     clearly
    0.52
    だろうか
    0.50
     trông
    0.50
     APPE
    0.49
    findpost
    0.49
     appear
    0.48
     visibly
    0.47
    sworth
    0.46
     appearance
    0.46
    behavior
    0.46
    Activations Density 0.227%

    No Known Activations