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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16000
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize concentration and prioritization

    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
     downloadable
    -0.43
     VIDEOTAPE
    -0.39
     artist
    -0.39
     ridden
    -0.39
     enfans
    -0.39
     boleto
    -0.38
    
    -0.38
     airline
    -0.38
     installa
    -0.38
     simulate
    -0.37
    POSITIVE LOGITS
     focus
    1.39
    focus
    1.36
    Focus
    1.26
     Focus
    1.25
     FOCUS
    1.18
    FOCUS
    1.16
     focuses
    1.16
     focused
    1.13
    ocusing
    1.12
     focussed
    1.12
    Activations Density 0.145%

    No Known Activations