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. 20-GEMMASCOPE-RES-16K
    6. 7288
    Prev
    Next
    INDEX
    Explanations

    comparisons between two or more entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    On the other hand

    np_acts-logits-general · gemini-2.0-flash

    other hand / one hand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RectangleBorder
    -1.17
     ویکی‌پدیا
    -1.17
     pinulongan
    -1.01
    ьаж
    -0.95
    Portail
    -0.92
     ſtate
    -0.90
    InstrumentedTest
    -0.89
    httphttps
    -0.87
     laſt
    -0.87
     faſt
    -0.86
    POSITIVE LOGITS
    <eos>
    0.62
    ↵↵↵
    0.53
    ‎
    0.47
    ↵↵
    0.45
    ĺ
    0.42
     I
    0.42
    ’
    0.41
    ↵
    0.41
     
    0.41
    ‌‌
    0.41
    Activations Density 0.408%

    No Known Activations