Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 5930
    Prev
    Next
    INDEX
    Explanations

    references to different applications or uses of technology

    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
     animación
    -0.48
     mío
    -0.48
     nahilalakip
    -0.48
     ejecutivo
    -0.47
    OGND
    -0.47
     zijne
    -0.46
    VYMaps
    -0.45
     otomatig
    -0.44
     dumne
    -0.43
    новниш
    -0.42
    POSITIVE LOGITS
     Applications
    1.23
    Application
    1.10
    Applications
    1.06
     Application
    0.98
     APPLICATIONS
    0.94
     applications
    0.94
    APPLICATIONS
    0.75
     App
    0.72
    App
    0.67
     Applied
    0.67
    Activations Density 0.045%

    No Known Activations