© 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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 13262
    Prev
    Next
    INDEX
    Explanations

    commands or prompts to interact with content, typically links or buttons

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

    Followed by "here", "on", "to", or "below"

    np_acts-logits-general · gemini-2.0-flash

    click here

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    aarrggbb
    -0.71
    المناصب
    -0.63
     <=",
    -0.61
     ModelRenderer
    -0.60
    Дереккөздер
    -0.60
    <tfoot>
    -0.57
     Uff
    -0.56
     bezeichneter
    -0.55
    IMPORTED
    -0.54
    MemoryWarning
    -0.54
    POSITIVE LOGITS
    bait
    0.85
    ety
    0.69
     bait
    0.58
    Bait
    0.56
     مشين
    0.56
     play
    0.55
     anywhere
    0.53
     here
    0.52
     button
    0.51
     image
    0.50
    Activations Density 0.060%

    No Known Activations