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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 13692
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to jury proceedings and trials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gedanken
    -0.56
     Schie
    -0.55
    mişti
    -0.53
     hình
    -0.52
     hang
    -0.51
     Higgs
    -0.51
    Higgs
    -0.48
    nase
    -0.48
    ⇄
    -0.48
     tunggu
    -0.47
    POSITIVE LOGITS
    ich
    1.39
    ская
    1.02
    ской
    0.94
    скую
    0.85
    ского
    0.85
    makeConstraints
    0.85
    ICH
    0.83
     كومونز
    0.82
    ский
    0.82
    ских
    0.73
    Activations Density 0.044%

    No Known Activations