© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 3910
    Prev
    Next
    INDEX
    Explanations

    specific structured data attributes and keywords related to technical standards and requirements

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

    after opening quotation marks

    np_acts-logits-general · gemini-2.0-flash

    quoted phrases or special terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endphp
    -0.35
     
    -0.29
     admitted
    -0.28
     admitting
    -0.28
     EconPapers
    -0.28
     admit
    -0.28
     FBref
    -0.27
     And
    -0.27
    And
    -0.27
    tahankan
    -0.27
    POSITIVE LOGITS
     ProtoMessage
    0.61
     Италијани
    0.60
    WEBPACK
    0.60
    CodedInputStream
    0.60
    لينكات
    0.56
    PreferredItem
    0.56
    setVerticalGroup
    0.56
    niſſe
    0.55
    :✨
    0.54
    rrggbb
    0.54
    Activations Density 0.301%

    No Known Activations