© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7667
    Prev
    Next
    INDEX
    Explanations

    references to events and their attributes

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

    The token "event" and related terms

    np_acts-logits-general · gemini-2.0-flash

    event rates and metadata

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hivatalos
    -0.44
     barata
    -0.41
     financiero
    -0.40
     mijne
    -0.36
     glauben
    -0.36
     kebijakan
    -0.35
     förb
    -0.35
     Kebijakan
    -0.34
     automatiques
    -0.34
     lisäksi
    -0.33
    POSITIVE LOGITS
     Event
    1.21
     events
    1.15
     event
    1.13
     Events
    1.10
     EVENT
    1.04
     evt
    1.02
     eventId
    0.96
     EVENTS
    0.96
    Event
    0.93
    getEvent
    0.90
    Activations Density 0.098%

    No Known Activations