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. 10-GEMMASCOPE-RES-16K
    6. 3463
    Prev
    Next
    INDEX
    Explanations

    guidelines for behavior in social or formal dining situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.84
     Signalez
    -0.77
     Vikipedi
    -0.75
     picioare
    -0.73
     estekak
    -0.72
     dieux
    -0.71
     financières
    -0.71
     veau
    -0.70
     âmes
    -0.70
    Hochspringen
    -0.69
    POSITIVE LOGITS
     pre
    0.51
     
    0.50
     A
    0.50
     Bag
    0.49
     the
    0.48
     social
    0.48
     metal
    0.47
     natural
    0.47
     In
    0.46
     true
    0.46
    Activations Density 0.690%

    No Known Activations