© 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. 9349
    Prev
    Next
    INDEX
    Explanations

    points of significant document structure or markers like "beginning" and "end"

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

    Follows certain special characters/symbols

    np_acts-logits-general · gemini-2.0-flash

    conventional methods

    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
     Bioaccumulative
    -0.59
    s
    -0.59
     ​
    -0.58
     Monfieur
    -0.57
     DBNull
    -0.55
    ,’”
    -0.54
    extAlignment
    -0.53
    sthe
    -0.52
     Theſe
    -0.52
     tot
    -0.52
    POSITIVE LOGITS
    KommentareTeilen
    0.70
     оригіналу
    0.70
    <unused61>
    0.67
    <unused63>
    0.64
     للاسماء
    0.62
    <unused62>
    0.62
    PYX
    0.61
    <unused60>
    0.59
    AppMethodBeat
    0.59
    <?
    0.58
    Activations Density 0.240%

    No Known Activations