© 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. 35-GEMMASCOPE-RES-16K
    11. 14068
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific measurements and experimental setups

    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
    ɵɵelementEnd
    -0.45
    artifactId
    -0.35
     Drums
    -0.34
     Posters
    -0.34
     Ensign
    -0.33
    手中的
    -0.32
     دار
    -0.31
     aload
    -0.31
    SEMICOLON
    -0.31
    >
    -0.31
    POSITIVE LOGITS
    GEBURTS
    0.68
     COVID
    0.67
    ItemBackground
    0.61
     coronavirus
    0.61
     Covid
    0.60
     pandemic
    0.60
     covid
    0.60
     Brexit
    0.60
    COVID
    0.60
    pandemic
    0.60
    Activations Density 4.427%

    No Known Activations