© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 14627
    Prev
    Next
    INDEX
    Explanations

    philosophical concepts and discussions

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

    Follows punctuation, introduces contrasting information

    np_acts-logits-general · gemini-2.0-flash

    connects idea A. However, idea B

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelf
    -0.81
    featureID
    -0.78
    ſelves
    -0.73
    wiſe
    -0.72
     juſ
    -0.70
     itſelf
    -0.67
    MigrationBuilder
    -0.66
     myſelf
    -0.66
     faſt
    -0.65
     ſta
    -0.63
    POSITIVE LOGITS
     what
    1.06
    what
    0.83
    What
    0.76
    唯一
    0.69
     What
    0.67
     самое
    0.65
     آنچه
    0.63
    最
    0.63
     biggest
    0.61
    最大的
    0.61
    Activations Density 0.627%

    No Known Activations