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. 41-GEMMASCOPE-RES-16K
    6. 10474
    Prev
    Next
    INDEX
    Explanations

    expressions of motivation and enthusiasm for teaching and helping others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ScopeManager
    -0.61
    存于互联网档案馆
    -0.42
     sää
    -0.40
    WithIOException
    -0.40
     OFDb
    -0.39
     silêncio
    -0.38
    eramente
    -0.38
     רח
    -0.37
    chio
    -0.37
     SUDOC
    -0.36
    POSITIVE LOGITS
     energy
    1.48
     energi
    1.41
     energ
    1.41
     energized
    1.38
     energetic
    1.35
     enthusiasm
    1.32
     energie
    1.27
     energía
    1.23
    energy
    1.20
    energ
    1.20
    Activations Density 0.433%

    No Known Activations