© 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. 3-GEMMASCOPE-RES-16K
    11. 8487
    Prev
    Next
    INDEX
    Explanations

    specific proper nouns and technical terms related to diverse contexts such as law, medicine, and data analysis

    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
    marginBottom
    -0.38
    BaseController
    -0.38
     Schluß
    -0.38
    HideFlags
    -0.38
     vêtement
    -0.37
     mennes
    -0.37
     Stunde
    -0.37
     dům
    -0.36
    EClass
    -0.36
     Werkzeug
    -0.36
    POSITIVE LOGITS
    ane
    0.74
    registry
    0.71
    Registry
    0.70
     registry
    0.67
     Registry
    0.64
    Dale
    0.63
     Dale
    0.60
     rally
    0.60
    ANE
    0.60
    trace
    0.58
    Activations Density 1.296%

    No Known Activations