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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 894
    Prev
    Next
    INDEX
    Explanations

    time-related information and scheduling details

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

    times of day and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.81
    rungsseite
    -0.80
    GEBURTSDATUM
    -0.79
     queſta
    -0.79
    featureID
    -0.77
    __*/
    -0.73
    InputBorder
    -0.73
     виправивши
    -0.71
    省市镇
    -0.68
    Viited
    -0.67
    POSITIVE LOGITS
     dimulai
    0.27
     empe
    0.26
     noon
    0.26
     гран
    0.26
     beginning
    0.26
     midday
    0.26
    開始
    0.25
    łami
    0.25
    开始
    0.25
     mediodía
    0.24
    Activations Density 0.005%

    No Known Activations