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. 15382
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, particularly Jared Kushner, in relation to various political and financial contexts

    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
     `.
    -1.02
    ed
    -0.98
     Duckworth
    -0.96
    a
    -0.96
    т
    -0.92
     Schuster
    -0.89
     Beller
    -0.86
    +#+#
    -0.86
     Armstrong
    -0.85
    tempted
    -0.84
    POSITIVE LOGITS
    ness
    0.92
    URLException
    0.92
    TestingModule
    0.78
     Pogba
    0.77
    drawiam
    0.77
    Kush
    0.74
    tagext
    0.73
     Millard
    0.73
     Faul
    0.72
    erir
    0.71
    Activations Density 2.557%

    No Known Activations