© 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. 128235
    Prev
    Next
    INDEX
    Explanations

    sequences of characters resembling formatting or structural elements in documents

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

    mathematical array or repeated character sequences

    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
     BoxDecoration
    -0.43
    createStatement
    -0.41
    prepareStatement
    -0.41
    NSError
    -0.40
    lioz
    -0.40
    誼
    -0.39
    IRAN
    -0.38
    netinet
    -0.38
    cstdlib
    -0.38
     Chowdhury
    -0.37
    POSITIVE LOGITS
    llllllll
    1.21
    lllllllll
    1.16
    lllllll
    1.06
    lcccccc
    0.99
    llllll
    0.90
    ccccccc
    0.84
    cccccccc
    0.77
    lccccc
    0.69
    cccccc
    0.63
     дописавши
    0.61
    Activations Density 0.003%

    No Known Activations