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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 7693
    Prev
    Next
    INDEX
    Explanations

    events hosted or organized by institutions and their associated personnel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.57
    γη
    -0.50
    لكتر
    -0.49
     bambú
    -0.45
     aéri
    -0.45
    matis
    -0.43
    lè
    -0.42
    Dữ
    -0.41
     critical
    -0.41
    googleapis
    -0.41
    POSITIVE LOGITS
     surla
    0.95
    CppMethod
    0.78
    FTFY
    0.63
     通販
    0.63
    RotationOrder
    0.59
     שוליים
    0.58
    esModule
    0.58
    ensión
    0.58
    intios
    0.58
     bArr
    0.58
    Activations Density 0.154%

    No Known Activations