Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4443
    Prev
    Next
    INDEX
    Explanations

    instances of slashes and parentheses in the text

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

    Text after a forward slash

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions and fractions

    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
    (
    -1.20
    -
    -1.15
    .
    -0.93
    *
    -0.84
    [
    -0.84
    :
    -0.73
    \
    -0.72
    _
    -0.70
    ,
    -0.69
    $
    -0.69
    POSITIVE LOGITS
     $/$
    1.01
     $/
    1.00
    ../
    0.92
    {}/
    0.92
    ˈ
    0.84
     itſelf
    0.81
    |/
    0.79
    .../
    0.76
     utafitiHapana
    0.76
    PRNewswire
    0.74
    Activations Density 0.348%

    No Known Activations