© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105647
    Prev
    Next
    INDEX
    Explanations

    references to errors or technical issues

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

    Single tokens or short sequences appearing in technical text, documentation, and formatted content, often representing parts of identifiers, numbers, or specialized terminology.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.70
    Хьажоргаш
    -0.63
    GEBURTSDATUM
    -0.62
     beginnetje
    -0.60
     ligiloj
    -0.55
    adaptiveStyles
    -0.55
     الرياضيه
    -0.54
     nakalista
    -0.53
     ddelweddau
    -0.51
    rrggbb
    -0.50
    POSITIVE LOGITS
    
    0.41
    IActionResult
    0.39
    enapa
    0.37
     Wey
    0.37
    EntityFramework
    0.36
    PullParser
    0.36
    PropertyChanging
    0.36
     arre
    0.35
     SOU
    0.35
     mijne
    0.35
    Activations Density 0.166%

    No Known Activations