© 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. 24-GEMMASCOPE-RES-16K
    11. 8979
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate significant subjects or topics in a research context

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

    after "focus," "subject," or similar terms

    np_acts-logits-general · gemini-2.0-flash

    focus of attention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -0.66
     ſch
    -0.58
    wiſe
    -0.57
    UnusedPrivate
    -0.57
    Становништво
    -0.54
     ſy
    -0.53
     Chriftian
    -0.52
    archiviato
    -0.51
     leaſt
    -0.51
    rsiniz
    -0.51
    POSITIVE LOGITS
     focus
    0.57
     priority
    0.50
     priorities
    0.44
     foco
    0.43
     preoccupation
    0.40
    focus
    0.40
     focuses
    0.40
     devotes
    0.40
     priorité
    0.39
     Focus
    0.38
    Activations Density 0.421%

    No Known Activations