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-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 8199
    Prev
    Next
    INDEX
    Explanations

     commands related to resetting configurations or settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olische
    -0.49
     protoimpl
    -0.49
     lilla
    -0.46
     koron
    -0.46
    Искәрмәләр
    -0.46
     commerciaux
    -0.45
     décédé
    -0.44
     françaises
    -0.44
     financières
    -0.44
    Décès
    -0.44
    POSITIVE LOGITS
     reset
    0.87
     Reset
    0.83
    Reset
    0.78
     resets
    0.78
    reset
    0.75
    重置
    0.74
     RESET
    0.72
    \{\\
    0.71
     resetting
    0.70
    SharedCtor
    0.69
    Activations Density 0.194%

    No Known Activations