© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4015
    Prev
    Next
    INDEX
    Explanations

    instances of the word "every" and its variations, indicating a focus on universality or inclusiveness in context

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

    repeated words like "Every" and quantifier words like "one", "of", "bit", "time".

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    AEL
    -0.39
     Jiao
    -0.35
    S
    -0.34
     Brunch
    -0.34
     Ismael
    -0.33
     Agreement
    -0.33
     agreement
    -0.32
      
    -0.32
    D
    -0.32
    ルト
    -0.31
    POSITIVE LOGITS
    every
    1.57
     every
    1.55
     Every
    1.48
    Every
    1.47
     EVERY
    1.45
    EVERY
    1.30
    Ogni
    1.14
     setiap
    1.06
     Ogni
    1.04
     ogni
    1.03
    Activations Density 0.061%

    No Known Activations