© 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. 105786
    Prev
    Next
    INDEX
    Explanations

    repeated letter sequences primarily consisting of the letter 'l'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    transQ
    -0.92
    RenderAtEndOf
    -0.87
    thâu
    -0.85
    ágenes
    -0.78
    __(/*!
    -0.77
     ErrInvalid
    -0.73
     TextAppearance
    -0.71
     विश्वसनीयता
    -0.70
    PreferredItem
    -0.70
     nahilalakip
    -0.70
    POSITIVE LOGITS
    l
    0.68
    L
    0.60
     L
    0.55
     l
    0.50
    ll
    0.44
    lll
    0.44
    T
    0.42
    Л
    0.41
    H
    0.41
    llll
    0.41
    Activations Density 0.001%

    No Known Activations