© 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. 3-GEMMASCOPE-RES-16K
    11. 6419
    Prev
    Next
    INDEX
    Explanations

    specific proper nouns and terminology related to botany and cinema

    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
     GIPHY
    -0.50
     Murdoch
    -0.48
    xff
    -0.46
     endTime
    -0.45
    webkit
    -0.44
    pageY
    -0.43
    JoinColumn
    -0.42
    ClientID
    -0.42
     Wett
    -0.41
    providedIn
    -0.41
    POSITIVE LOGITS
    er
    0.98
    ergic
    0.75
    erick
    0.69
    erle
    0.67
    erate
    0.66
     Tirana
    0.64
     miniaturka
    0.63
    erl
    0.62
    erti
    0.61
    eria
    0.61
    Activations Density 5.833%

    No Known Activations