© 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. 10-GEMMASCOPE-RES-16K
    11. 7133
    Prev
    Next
    INDEX
    Explanations

    references to specific venues and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yoghurt
    -0.69
     enquiry
    -0.68
     learnt
    -0.66
     Maths
    -0.66
     beetroot
    -0.65
     maths
    -0.64
     tyre
    -0.64
    paedia
    -0.63
     woollen
    -0.63
     formulae
    -0.61
    POSITIVE LOGITS
    Harbor
    0.91
     Harbor
    0.89
     Theater
    0.85
    hitheater
    0.85
    Theater
    0.81
     theater
    0.76
     DEFENSE
    0.74
     Travelers
    0.72
     ๆ
    0.71
    Canceled
    0.71
    Activations Density 3.643%

    No Known Activations