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-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 5750
    Prev
    Next
    INDEX
    Explanations

    medical conditions and their complications, particularly those related to inflammatory diseases and surgery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ьаж
    -0.55
    AnchorTagHelper
    -0.54
    ScopeManager
    -0.48
    InjectAttribute
    -0.43
    الحياه
    -0.42
    AndEndTag
    -0.40
     فريبيس
    -0.39
    IsMutable
    -0.38
    NOPQRST
    -0.37
     biens
    -0.37
    POSITIVE LOGITS
     secondary
    1.19
    secondary
    0.96
     Secondary
    0.93
    Secondary
    0.89
     secundaria
    0.88
     secondaire
    0.88
     secundario
    0.85
     SECONDARY
    0.85
    SECONDARY
    0.73
     secondaires
    0.72
    Activations Density 2.577%

    No Known Activations