© 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. 100992
    Prev
    Next
    INDEX
    Explanations

    numerical data related to events or statistics

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

    years preceding events

    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
    SequentialGroup
    -0.54
     Autorisations
    -0.50
    IntoConstraints
    -0.50
     OFDb
    -0.49
    AutoScaleMode
    -0.49
     Autorizaciones
    -0.47
    arrêter
    -0.47
    XmlAccessorType
    -0.46
     auroit
    -0.45
     فريبيس
    -0.45
    POSITIVE LOGITS
     Moroccan
    0.56
     Belgian
    0.54
     Brazilian
    0.53
     Venezuelan
    0.51
     Victorian
    0.51
     annual
    0.51
     Cuban
    0.51
     recent
    0.51
     Colombian
    0.51
     Nigerian
    0.50
    Activations Density 0.044%

    No Known Activations