© 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. 15469
    Prev
    Next
    INDEX
    Explanations

    programming constructs and patterns typically used in coding environments

    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
     with
    -1.91
     dengan
    -1.15
     với
    -1.07
     avec
    -1.01
     עם
    -0.95
    กับ
    -0.94
    with
    -0.91
    avec
    -0.88
     wraz
    -0.83
     със
    -0.82
    POSITIVE LOGITS
     versehen
    0.84
     ausgestattet
    0.69
    为例
    0.54
     intact
    0.45
     proviso
    0.41
    cstdio
    0.38
     Schwerpunkt
    0.37
     BoxFit
    0.36
     accents
    0.36
     Mitteln
    0.36
    Activations Density 0.762%

    No Known Activations