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. 3742
    Prev
    Next
    INDEX
    Explanations

    phrases indicating collaboration and international partnerships

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

    Adjectives following articles or demonstratives

    np_acts-logits-general · gemini-2.0-flash

    first impression

    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
    EndInit
    -0.82
    GraphicsUnit
    -0.69
    MemoryWarning
    -0.67
    mybatisplus
    -0.67
     prossima
    -0.60
    exitRule
    -0.60
    TestingModule
    -0.58
     zijne
    -0.56
     moglie
    -0.56
    出版年
    -0.56
    POSITIVE LOGITS
    orice
    0.63
    ToListAsync
    0.60
    baugh
    0.54
     albeit
    0.53
    onViewCreated
    0.52
    蚪
    0.51
    rovnik
    0.51
    Saxon
    0.50
    )}>
    0.50
    yntaxException
    0.50
    Activations Density 0.300%

    No Known Activations