© 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. 11-GEMMASCOPE-RES-16K
    11. 13683
    Prev
    Next
    INDEX
    Explanations

    references to events and organizers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.70
    TagHelper
    -0.63
    addCriterion
    -0.61
    ThroughAttribute
    -0.60
    $_['
    -0.59
     виправивши
    -0.59
     tjän
    -0.58
    ForValue
    -0.58
    AccessorTable
    -0.57
     sagesse
    -0.56
    POSITIVE LOGITS
     events
    1.02
     event
    0.94
     venue
    0.84
     Events
    0.81
     EVENTS
    0.80
     evenement
    0.79
     Veranstaltungen
    0.78
     evento
    0.77
     Veranstaltung
    0.77
     venues
    0.76
    Activations Density 0.342%

    No Known Activations