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. 4355
    Prev
    Next
    INDEX
    Explanations

    phrases related to product descriptions and specifications

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

    Replacement parts or alternatives

    np_acts-logits-general · gemini-2.0-flash

    replacement parts

    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
     doInBackground
    -0.79
    BeginInit
    -0.70
     BoxFit
    -0.69
    PMailer
    -0.64
    ftagPool
    -0.64
     ModelExpression
    -0.64
    tagext
    -0.63
    ContentAsync
    -0.63
    onViewCreated
    -0.62
     Ibn
    -0.62
    POSITIVE LOGITS
     replacement
    1.27
     Replacement
    1.14
     replacements
    1.14
    Replacement
    1.11
     compatible
    1.05
    replacement
    1.01
     compatibles
    0.99
     Compatible
    0.95
     remplacement
    0.91
     aftermarket
    0.89
    Activations Density 0.200%

    No Known Activations