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. 9186
    Prev
    Next
    INDEX
    Explanations

    mentions of names, naming conventions, and their formal representations

    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
     للمعارف
    -0.95
     متعلقه
    -0.84
     समीक्षाओं
    -0.79
    ValueStyle
    -0.76
     UserProfile
    -0.62
    üyada
    -0.62
    -------------</
    -0.62
    afficheront
    -0.61
     ProtoMessage
    -0.61
    IsContent
    -0.61
    POSITIVE LOGITS
    listdir
    0.69
    rename
    0.69
     naming
    0.69
     names
    0.69
     rename
    0.68
     name
    0.68
    Naming
    0.64
    naming
    0.61
    命名
    0.59
     Naming
    0.56
    Activations Density 0.315%

    No Known Activations