© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 10230
    Prev
    Next
    INDEX
    Explanations

    instances of the word "focus" indicating an emphasis on specific topics or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.42
    NewLabel
    -0.39
    leine
    -0.35
    isMethod
    -0.35
    цар
    -0.35
     UITableView
    -0.34
    ressible
    -0.34
     munici
    -0.34
     indisponible
    -0.33
    SharedDtor
    -0.33
    POSITIVE LOGITS
     focus
    4.38
    focus
    3.98
     Focus
    3.80
    Focus
    3.78
     FOCUS
    3.22
    FOCUS
    3.13
     Fokus
    3.00
     fokus
    2.91
     focuses
    2.63
     foco
    2.50
    Activations Density 0.067%

    No Known Activations