© 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. 3-GEMMASCOPE-RES-16K
    11. 10462
    Prev
    Next
    INDEX
    Explanations

    words indicating strong or significant mention of events or specific details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.69
     Wikispecies
    -0.54
    ⓧ
    -0.53
    //
    -0.51
    éry
    -0.51
    Tikang
    -0.50
    OGND
    -0.49
     CanadaChoose
    -0.47
     Rag
    -0.47
    loma
    -0.47
    POSITIVE LOGITS
    Personendaten
    0.46
     vuelto
    0.34
     препратки
    0.32
     AspNetCore
    0.32
     combinación
    0.32
     ollut
    0.31
     transparencia
    0.30
     liksom
    0.30
    ushchev
    0.30
    Rüyada
    0.30
    Activations Density 0.382%

    No Known Activations