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. 2960
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to Delaware law

    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
    berspace
    -0.69
    Rahman
    -0.67
    chaik
    -0.65
     Healey
    -0.64
    ußen
    -0.64
    oglobin
    -0.63
    Megan
    -0.63
    poxy
    -0.63
     Marburg
    -0.63
    Dres
    -0.62
    POSITIVE LOGITS
     препратки
    0.96
    Diwedd
    0.91
    例句
    0.90
     cár
    0.82
    Edel
    0.81
     citoy
    0.81
    optString
    0.79
    oltre
    0.79
    хьтан
    0.78
    Dele
    0.77
    Activations Density 0.913%

    No Known Activations