© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 3733
    Prev
    Next
    INDEX
    Explanations

    structural elements of HTML or web layout components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HTML/code snippets

    np_acts-logits-general · gemini-2.0-flash

    HTML structure and CSS classes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.56
    ymce
    -0.53
    httphttps
    -0.49
    RTLR
    -0.49
     >=",
    -0.47
     jadx
    -0.47
    adaptiveStyles
    -0.46
     كومونز
    -0.46
    étal
    -0.45
    glTexCoord
    -0.45
    POSITIVE LOGITS
    exitRule
    0.47
     bambú
    0.36
     Earth
    0.35
     Romains
    0.33
     mapStateToProps
    0.33
     girasol
    0.33
     personnalisées
    0.33
    ObjectContext
    0.32
     doit
    0.32
     statistique
    0.32
    Activations Density 0.042%

    No Known Activations