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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14715
    Prev
    Next
    INDEX
    Explanations

    references to concentration and focus on specific tasks or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enfans
    -0.44
    UserScript
    -0.43
     IAP
    -0.42
    
    -0.42
    FlatAppearance
    -0.42
    IsMutable
    -0.41
     simulate
    -0.41
     Robotic
    -0.41
    Personensuche
    -0.40
     artist
    -0.40
    POSITIVE LOGITS
     focus
    1.38
    focus
    1.35
    Focus
    1.23
     Focus
    1.20
     focussed
    1.16
     FOCUS
    1.16
    FOCUS
    1.16
     focussing
    1.12
     focuses
    1.12
     focused
    1.12
    Activations Density 0.185%

    No Known Activations