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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 11419
    Prev
    Next
    INDEX
    Explanations

    references to physical injuries and wounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     antwoord
    -0.46
    eseorang
    -0.46
     compagnia
    -0.45
     bencana
    -0.44
     nadzieję
    -0.43
     تعدى
    -0.43
    awtextra
    -0.43
    płat
    -0.43
     actitudes
    -0.42
     bezit
    -0.42
    POSITIVE LOGITS
    
    0.56
    IVEREF
    0.52
     THEIR
    0.48
     nakalista
    0.48
     Italijanski
    0.47
    Rohy
    0.43
     intim
    0.42
     Frei
    0.41
     sore
    0.41
    AddTagHelper
    0.40
    Activations Density 0.453%

    No Known Activations