© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4912
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols used in programming or markup languages

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

    "rows" or "rails" followed by other tokens

    np_acts-logits-general · gemini-2.0-flash

    rows, removals, or database rows

    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
    GEBURTSDATUM
    -0.69
    AddTagHelper
    -0.63
    TagMode
    -0.57
    帖最后由
    -0.56
    PreferredItem
    -0.56
    ReusableCell
    -0.53
     مواليد
    -0.53
    Erreferentziak
    -0.52
    thansa
    -0.52
     snippetHide
    -0.50
    POSITIVE LOGITS
    rows
    0.92
     rows
    0.89
     Reynolds
    0.85
     rs
    0.83
     Rees
    0.80
     rings
    0.80
     rules
    0.80
     rangers
    0.79
     reefs
    0.77
    routes
    0.76
    Activations Density 0.212%

    No Known Activations