© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 128407
    Prev
    Next
    INDEX
    Explanations

    symbols and syntax structures commonly used in programming languages

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

    internal code and libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.71
     ब्रेकडाउन
    -0.71
    rrggbb
    -0.69
    MessageTagHelper
    -0.68
    posedge
    -0.68
    FormTagHelper
    -0.68
     actionMode
    -0.66
    ItemBackground
    -0.66
    aarrggbb
    -0.65
    ंदीखरीदारी
    -0.65
    POSITIVE LOGITS
     internal
    0.84
    internal
    0.80
     Internal
    0.79
    Internal
    0.77
    INTERNAL
    0.73
     INTERNAL
    0.62
    内部
    0.61
     internally
    0.59
     interno
    0.54
     internals
    0.53
    Activations Density 0.007%

    No Known Activations