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. 20-GEMMASCOPE-RES-16K
    6. 9324
    Prev
    Next
    INDEX
    Explanations

    metrics related to sports performance statistics

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

    Code snippets and technical language

    np_acts-logits-general · gemini-2.0-flash

    structured data formats

    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
    Whilst
    -0.95
     Whilst
    -0.94
     sixty
    -0.73
     whilst
    -0.73
     thirteen
    -0.72
     twenty
    -0.72
     Amongst
    -0.72
    Alright
    -0.69
     fifteen
    -0.67
     thirty
    -0.67
    POSITIVE LOGITS
    enumii
    0.62
    BeginContext
    0.59
     vorigen
    0.56
    ‴
    0.54
     nedenle
    0.54
    ◗
    0.53
    kuuta
    0.53
     ★★★
    0.52
     ‘‘
    0.52
    ∛
    0.52
    Activations Density 0.361%

    No Known Activations