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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-GEMMASCOPE-RES-16K
    6. 1403
    Prev
    Next
    INDEX
    Explanations

    terms related to organizational structures and developments

    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
    ViewFeatures
    -1.00
    parsedMessage
    -0.90
     GenerationType
    -0.86
    IntoConstraints
    -0.77
     AssemblyCulture
    -0.75
    TagMode
    -0.75
     ModelExpression
    -0.73
     itſelf
    -0.73
    SharedCtor
    -0.72
     Paglinawan
    -0.71
    POSITIVE LOGITS
     for
    0.44
    Cle
    0.43
    หนึ่ง
    0.43
    Gain
    0.42
    меча
    0.40
    ึ่ง
    0.40
     used
    0.40
     Lab
    0.40
     Gain
    0.39
     co
    0.39
    Activations Density 0.885%

    No Known Activations