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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 978
    Prev
    Next
    INDEX
    Explanations

    references to ownership and control of personal data

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

    Comes before capitalized abbreviations

    np_acts-logits-general · gemini-2.0-flash

    foreign and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.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
     a
    -0.38
     Cher
    -0.34
    ActionMode
    -0.33
    据
    -0.32
    .
    -0.31
    digkeit
    -0.31
     Mob
    -0.31
    dAtA
    -0.31
     Walker
    -0.30
     Park
    -0.29
    POSITIVE LOGITS
    setupUi
    0.74
    ніципалі
    0.68
     Geſch
    0.64
    oredCriteria
    0.63
    CloseOperation
    0.63
    帖最后由
    0.63
     وتسجيلات
    0.61
     queſta
    0.60
    tanleria
    0.60
    ließlich
    0.59
    Activations Density 0.845%

    No Known Activations