© 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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 11853
    Prev
    Next
    INDEX
    Explanations

    legal terms and conditions related to software and liability

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

    appearing before "IN" or "INGS"

    np_acts-logits-general · gemini-2.0-flash

    programming license boilerplates

    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
     <",
    -0.36
     loyal
    -0.36
    Sklici
    -0.35
     public
    -0.35
     working
    -0.35
    PlayerPrefs
    -0.35
     fhew
    -0.34
     theatre
    -0.33
    xique
    -0.33
     isNameExpr
    -0.32
    POSITIVE LOGITS
    AccessorTable
    1.05
     AssemblyCulture
    0.94
    autoreleasepool
    0.88
     виправивши
    0.88
    IndentedString
    0.86
     ویکی‌پدیای
    0.83
    
    0.82
    parsedMessage
    0.82
    AnchorStyles
    0.80
    WriteBarrier
    0.79
    Activations Density 0.480%

    No Known Activations