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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 15688
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/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.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.73
    AddHtmlAttribute
    -0.69
    principalColumn
    -0.66
    ConstraintMaker
    -0.66
    MLLoader
    -0.64
     يتيمه
    -0.63
    verwijspagina
    -0.62
    EDEFAULT
    -0.62
    Архівовано
    -0.62
    addCriterion
    -0.62
    POSITIVE LOGITS
    ’
    0.47
    JAKARTA
    0.44
    '
    0.44
    <h1>
    0.39
    本文
    0.39
    //
    0.38
    Transkript
    0.36
    <h2>
    0.36
    Jakarta
    0.35
    Liverpool
    0.35
    Activations Density 0.786%

    No Known Activations