© 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 EvalsExportsAPI 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. 1123
    Prev
    Next
    INDEX
    Explanations

    references and components related to XML processing and manipulation

    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
     consideración
    -0.37
    saraba
    -0.36
     fieltro
    -0.36
     הרב
    -0.35
    kuuta
    -0.35
     čo
    -0.35
    ########.
    -0.34
    omotor
    -0.33
    ρεύ
    -0.32
     חז
    -0.32
    POSITIVE LOGITS
    UnusedPrivate
    0.59
     ProtoMessage
    0.51
     XM
    0.47
     XB
    0.46
    thief
    0.45
    randomUUID
    0.45
     AssemblyCulture
    0.45
    aarrggbb
    0.44
    setCancelable
    0.44
     xm
    0.44
    Activations Density 0.181%

    No Known Activations