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. 10681
    Prev
    Next
    INDEX
    Explanations

    references to legal judgments or court opinions, including dates and related judicial terms

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

    Citations with numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by comma

    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
     for
    -0.57
    setArguments
    -0.56
    <bos>
    -0.56
     com
    -0.55
     as
    -0.51
    aws
    -0.50
    verket
    -0.50
    intellij
    -0.49
     (
    -0.49
     far
    -0.48
    POSITIVE LOGITS
    PasswordEncoder
    0.80
     snippetHide
    0.76
     myſelf
    0.72
     photolibrary
    0.71
     ―――――
    0.70
     ་་
    0.68
    ंदीखरीदारी
    0.67
     bezeichneter
    0.67
     Jefus
    0.66
     iſt
    0.66
    Activations Density 0.168%

    No Known Activations