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. 9-GEMMASCOPE-RES-16K
    6. 8018
    Prev
    Next
    INDEX
    Explanations

    statistical references and numerical data in scientific texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    piram
    -0.65
     Dummies
    -0.58
     ProtoMessage
    -0.57
    Билгалдахарш
    -0.56
    Външни
    -0.55
     للمعارف
    -0.54
    CloseOperation
    -0.54
    SequentialGroup
    -0.53
    hline
    -0.53
    IsMutable
    -0.52
    POSITIVE LOGITS
    出版年
    0.62
    リエーション
    0.58
    utives
    0.53
    getDoctrine
    0.48
     sabbia
    0.47
     kolei
    0.47
     appartiennent
    0.47
    argest
    0.46
     traités
    0.46
    largest
    0.45
    Activations Density 0.321%

    No Known Activations