© 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. 2985
    Prev
    Next
    INDEX
    Explanations

    references to specific physical positions or placements

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

    "position"

    np_acts-logits-general · gemini-2.0-flash

    position and relations

    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
    kfree
    -0.51
    WebServlet
    -0.48
    createNewFile
    -0.47
     trattano
    -0.47
     Endless
    -0.47
     Brooklyn
    -0.46
    Guerra
    -0.46
     Karls
    -0.45
    multirow
    -0.44
    TryParse
    -0.43
    POSITIVE LOGITS
     position
    1.26
     Position
    1.20
     POSITION
    1.18
    position
    1.14
    Position
    1.13
     positions
    1.13
     Positions
    1.11
     getPosition
    1.02
    getPosition
    0.98
    POSITION
    0.97
    Activations Density 0.192%

    No Known Activations