© 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. 95057
    Prev
    Next
    INDEX
    Explanations

    numerical values related to percentages and measurements

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

    3.5 followed by units or descriptions

    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
     EconPapers
    -0.61
     enfans
    -0.48
     exemplaires
    -0.48
    addContainerGap
    -0.47
    mær
    -0.47
     jäsen
    -0.46
    tonode
    -0.45
    ypeł
    -0.45
     olvido
    -0.45
     extérieures
    -0.43
    POSITIVE LOGITS
     four
    0.51
    SOUNDBITE
    0.46
     FetchType
    0.46
     MethodInfo
    0.44
    rowave
    0.42
     spaghetti
    0.42
     three
    0.42
     core
    0.41
    subsection
    0.41
     Welle
    0.41
    Activations Density 0.034%

    No Known Activations