Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3498
    Prev
    Next
    INDEX
    Explanations

    instances of the word "instead" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    囗
    -0.60
    userdetails
    -0.56
    Filmografia
    -0.52
    TemporalType
    -0.51
    Giới
    -0.49
    SourceChecksum
    -0.49
     صوتيه
    -0.48
    foly
    -0.48
    PerformLayout
    -0.47
     שוליים
    -0.47
    POSITIVE LOGITS
     instead
    1.09
    Instead
    1.03
     Instead
    0.97
    instead
    0.95
     rather
    0.81
    vece
    0.78
    Rather
    0.77
     вместо
    0.77
     zamiast
    0.76
     Rather
    0.73
    Activations Density 0.124%

    No Known Activations