© 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. 24-GEMMASCOPE-RES-16K
    11. 792
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components and their visibility in code

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

    CSS or Javascript keywords for hiding/displaying elements

    np_acts-logits-general · gemini-2.0-flash

    showing and hiding elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.60
     informée
    -0.56
    EDEFAULT
    -0.49
    NewUrlParser
    -0.46
    CrossRef
    -0.44
    ftagPool
    -0.43
    rrggbb
    -0.38
    RequestMapping
    -0.37
     cjs
    -0.36
    KommentareTeilen
    -0.36
    POSITIVE LOGITS
     hiding
    0.63
     hide
    0.60
    hide
    0.58
     visibilité
    0.57
     Visibility
    0.54
    visibility
    0.53
     visibility
    0.51
    hiding
    0.51
     Италијани
    0.51
     esconder
    0.50
    Activations Density 0.122%

    No Known Activations