© 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. 6700
    Prev
    Next
    INDEX
    Explanations

    references to size and measurements

    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
    dengar
    -0.27
    िल्ली
    -0.26
    jface
    -0.26
     قهر
    -0.25
     współ
    -0.25
     kendini
    -0.25
    setResult
    -0.24
    feinander
    -0.24
     ople
    -0.24
     Corte
    -0.23
    POSITIVE LOGITS
     size
    3.47
     sizes
    2.94
     Size
    2.92
    size
    2.89
    Size
    2.72
     SIZE
    2.67
     tamaño
    2.61
     sized
    2.55
     Sizes
    2.47
     Größe
    2.45
    Activations Density 0.990%

    No Known Activations