© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 8034
    Prev
    Next
    INDEX
    Explanations

    structure and syntax used in code, particularly related to programming languages and framework components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Grüsse
    -0.46
     Grecs
    -0.44
     egentligen
    -0.40
     pouvoit
    -0.39
     Ensino
    -0.38
    pAd
    -0.38
     trône
    -0.37
     Regno
    -0.37
     Inscrivez
    -0.36
    toHaveBeenCalled
    -0.36
    POSITIVE LOGITS
    WebElementEntity
    0.61
    AnchorStyles
    0.61
     transfieras
    0.59
    хьтан
    0.59
    ](#
    0.59
    sterious
    0.57
     חיצוניים
    0.55
     database
    0.54
    تقاوى
    0.54
     databases
    0.54
    Activations Density 0.539%

    No Known Activations