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

    Neuronpedia

    APICircuit 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. 16-GEMMASCOPE-RES-16K
    6. 6373
    Prev
    Next
    INDEX
    Explanations

    references to various artists and their contributions in music contexts

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

    Followed by examples or lists

    np_acts-logits-general · gemini-2.0-flash

    examples, lists, such as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.60
    RenderAtEndOf
    -0.59
    Hochspringen
    -0.54
     StatefulWidget
    -0.54
     AssemblyTitle
    -0.53
    EndProject
    -0.51
     Exacts
    -0.50
    .",
    
    -0.49
    micamente
    -0.48
     kind
    -0.48
    POSITIVE LOGITS
     such
    1.33
     like
    1.15
    例如
    1.09
    比如
    1.06
    such
    1.05
     tels
    0.98
     telles
    0.97
    如
    0.96
     including
    0.94
     takich
    0.94
    Activations Density 0.639%

    No Known Activations