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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5048
    Prev
    Next
    INDEX
    Explanations

    references to issues or editions of magazines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     дописавши
    -0.71
     تانيه
    -0.66
    UnusedPrivate
    -0.66
     CreateTagHelper
    -0.64
    BeginContext
    -0.63
     виправивши
    -0.60
    ruptedException
    -0.58
     مرئيه
    -0.56
     Wikispecies
    -0.55
    ytale
    -0.55
    POSITIVE LOGITS
     magazine
    1.69
     magazines
    1.42
     issue
    1.40
    magazine
    1.38
     Issue
    1.37
     Magazine
    1.34
    Issue
    1.26
    issue
    1.25
     Magazines
    1.18
    Magazine
    1.18
    Activations Density 0.235%

    No Known Activations