© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 7058
    Prev
    Next
    INDEX
    Explanations

    terms related to significant events or transitions in life and society

    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
     CreateTagHelper
    -0.63
    PYX
    -0.61
    WithIOException
    -0.57
    новништво
    -0.55
     ivelany
    -0.54
    DockStyle
    -0.53
     externi
    -0.53
     unknownFields
    -0.52
    
    -0.50
    ValueStyle
    -0.47
    POSITIVE LOGITS
     date
    0.87
     ceremony
    0.85
     ceremonies
    0.69
    date
    0.68
     announcement
    0.62
     Ceremony
    0.60
     rate
    0.59
     rites
    0.55
     imminent
    0.55
     dates
    0.55
    Activations Density 0.884%

    No Known Activations