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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 2724
    Prev
    Next
    INDEX
    Explanations

    references to focus or concentration in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Methuen
    -0.77
    Plata
    -0.69
     tubing
    -0.68
     Ingram
    -0.65
    lblNewLabel
    -0.64
    DeleteMapping
    -0.64
    umato
    -0.63
     thromb
    -0.63
     Schalke
    -0.63
    buatan
    -0.63
    POSITIVE LOGITS
     focus
    2.52
     Focus
    2.32
     FOCUS
    2.29
    FOCUS
    2.29
    focus
    2.25
    Focus
    2.24
     focuses
    2.12
     focussed
    2.11
     focused
    2.10
     focusing
    2.07
    Activations Density 0.050%

    No Known Activations