© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 3968
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and judicial evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ../
    -0.59
     ویکی‌پدیای
    -0.56
    contentLoaded
    -0.53
     resourceCulture
    -0.53
    uxxxx
    -0.52
    Datuak
    -0.49
     snippetHide
    -0.49
    ItemBackground
    -0.45
     protoimpl
    -0.45
    存于互联网档案馆
    -0.44
    POSITIVE LOGITS
     of
    2.94
    ของ
    1.30
     của
    1.15
    of
    1.06
     ofthe
    0.98
     Of
    0.86
     של
    0.78
     της
    0.78
    ofthe
    0.77
    Of
    0.76
    Activations Density 11.735%

    No Known Activations