© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 7070
    Prev
    Next
    INDEX
    Explanations

    the concept of utilizing or employing various tools or methods

    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
     usarlo
    -0.52
    如何
    -0.46
     cumplimiento
    -0.46
     cómo
    -0.42
     usage
    -0.42
     needing
    -0.42
     használat
    -0.42
     permitiendo
    -0.41
     funcionamento
    -0.41
     bagaimana
    -0.41
    POSITIVE LOGITS
     techniques
    0.93
     technology
    0.85
     tools
    0.76
     methods
    0.73
     existing
    0.70
     technologies
    0.69
    techniques
    0.69
     resources
    0.68
     computers
    0.68
     tactics
    0.68
    Activations Density 0.702%

    No Known Activations