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. 10178
    Prev
    Next
    INDEX
    Explanations

    the phrase "so-called"

    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
     snippetHide
    -0.68
     فريبيس
    -0.64
     Akismet
    -0.63
    saraba
    -0.63
     للمعارف
    -0.62
    Filmografia
    -0.59
    رشف
    -0.59
    Begriffsklä
    -0.59
    /*++
    -0.58
    addLast
    -0.58
    POSITIVE LOGITS
    called
    0.54
     disant
    0.48
     forth
    0.47
     lemn
    0.47
     respiration
    0.46
     far
    0.44
     called
    0.44
    SEQUENCE
    0.43
    akers
    0.43
     naselje
    0.43
    Activations Density 0.097%

    No Known Activations