© 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. 31-GEMMASCOPE-RES-16K
    11. 9668
    Prev
    Next
    INDEX
    Explanations

    technical terms and code-related structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numerical values and measurements in technical or scientific contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.80
    
    -0.80
    IndentedString
    -0.79
     ſei
    -0.77
    RenderAtEndOf
    -0.73
     myſelf
    -0.73
     ſind
    -0.72
    setVerticalGroup
    -0.71
    ikusbot
    -0.69
    Tembelea
    -0.69
    POSITIVE LOGITS
     dalamnya
    0.36
     Bewußt
    0.32
     appunto
    0.27
    页面存档备份
    0.27
     äl
    0.26
     daar
    0.26
    катери
    0.25
    ⣤
    0.25
     ervan
    0.25
     darum
    0.25
    Activations Density 0.543%

    No Known Activations