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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 9642
    Prev
    Next
    INDEX
    Explanations

    occurrences of function definitions and their structure in code

    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
     '\\;'
    -0.79
    twimg
    -0.71
    +#+#
    -0.71
    urlpatterns
    -0.70
    StructEnd
    -0.68
     disambiguazione
    -0.67
    rungsseite
    -0.66
    HasForeignKey
    -0.66
     estekak
    -0.65
    tvguidetime
    -0.63
    POSITIVE LOGITS
     tillbaka
    0.55
     tilbage
    0.47
    return
    0.47
     tilbake
    0.47
     ritorno
    0.46
     Савезне
    0.46
     soeur
    0.45
     först
    0.43
    نجليزية
    0.43
    Returns
    0.42
    Activations Density 0.104%

    No Known Activations