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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 15474
    Prev
    Next
    INDEX
    Explanations

    elements related to discussions and exchanges of information in a panel setting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    indd
    -0.64
     useDispatch
    -0.60
    iläum
    -0.59
     entrenar
    -0.52
    ัว
    -0.51
    Hauptartikel
    -0.51
    IUrlHelper
    -0.51
     CommonModule
    -0.50
     investigates
    -0.50
     türlü
    -0.50
    POSITIVE LOGITS
     introductions
    0.80
     reading
    0.73
     presenters
    0.70
     moderated
    0.69
     read
    0.69
     Announcements
    0.67
     unmute
    0.67
     motion
    0.66
     announcements
    0.66
     presentations
    0.65
    Activations Density 0.263%

    No Known Activations