© 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. 34-GEMMASCOPE-RES-16K
    11. 16002
    Prev
    Next
    INDEX
    Explanations

    programming and technical keywords related to configuration and command structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ੝
    -0.69
     Rake
    -0.62
     kef
    -0.61
     Peg
    -0.60
     PPM
    -0.60
    ðsíða
    -0.60
     calli
    -0.59
     clio
    -0.58
     Meter
    -0.57
     carav
    -0.57
    POSITIVE LOGITS
     utafitiHapana
    0.66
     Wikiseite
    0.61
     civilización
    0.53
     oreja
    0.51
    ⓧ
    0.48
     perfección
    0.47
     exploración
    0.46
    setVerticalGroup
    0.45
     ocupación
    0.44
     Italij
    0.44
    Activations Density 6.114%

    No Known Activations