© 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. 36-GEMMASCOPE-RES-16K
    11. 6280
    Prev
    Next
    INDEX
    Explanations

    specific elements of structured data or notation often used in scientific or academic writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.76
    ագրություններ
    -0.46
    KommentareTeilen
    -0.45
    isiaj
    -0.44
     kasarigan
    -0.44
     الرياضيه
    -0.43
    pirable
    -0.43
    izarse
    -0.42
     Monark
    -0.42
    httphttps
    -0.42
    POSITIVE LOGITS
     pos
    3.02
    pos
    2.69
     Pos
    2.56
    Pos
    2.44
     POS
    1.95
    POS
    1.94
     posa
    1.55
     posit
    1.46
    getPos
    1.45
     poser
    1.44
    Activations Density 0.298%

    No Known Activations