© 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. 35-GEMMASCOPE-RES-16K
    11. 7779
    Prev
    Next
    INDEX
    Explanations

    references to medical procedures and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     somewhat
    -0.90
    somewhat
    -0.84
     Somewhat
    -0.80
     biraz
    -0.77
     trochu
    -0.77
     trochę
    -0.75
     nieco
    -0.75
     agak
    -0.73
     cierta
    -0.70
    Somewhat
    -0.69
    POSITIVE LOGITS
     absolutely
    1.31
     unbelievably
    1.27
     incredibly
    1.21
     absolutamente
    1.21
    absolutely
    1.21
     utterly
    1.20
     абсолютно
    1.15
     literally
    1.15
     insanely
    1.15
     completely
    1.07
    Activations Density 4.039%

    No Known Activations