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. 4791
    Prev
    Next
    INDEX
    Explanations

    terms related to licenses and legal terminology in software documentation

    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
     Roskov
    -0.71
    BeginContext
    -0.64
     الاطلاع
    -0.62
    timewa
    -0.61
    AspNetCore
    -0.61
     AsyncTask
    -0.57
    DebuggerStep
    -0.57
     EdgeInsets
    -0.57
    classpath
    -0.56
     NSCoder
    -0.55
    POSITIVE LOGITS
    pshots
    0.48
    Razor
    0.46
    الحياه
    0.44
    дым
    0.43
     complements
    0.42
    🇶
    0.41
    GFX
    0.41
     cruda
    0.41
     pete
    0.40
     jspb
    0.40
    Activations Density 0.066%

    No Known Activations