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-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 6570
    Prev
    Next
    INDEX
    Explanations

    temporal phrases indicating specific moments or timelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     politiet
    -0.58
    例句
    -0.54
    جغرافيا
    -0.54
    itename
    -0.53
     revés
    -0.53
     Amaz
    -0.52
     reposer
    -0.52
     aktiviteter
    -0.51
    tangent
    -0.50
    ever
    -0.50
    POSITIVE LOGITS
    testens
    0.66
    chnet
    0.63
    ready
    0.62
    Бележки
    0.61
     lunchtime
    0.60
    脚注の使い方
    0.58
    TagMode
    0.58
     early
    0.58
     NSCoder
    0.57
    raisemb
    0.57
    Activations Density 0.108%

    No Known Activations