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. 13-GEMMASCOPE-RES-16K
    6. 8937
    Prev
    Next
    INDEX
    Explanations

    quantitative performance metrics and statistical analyses in research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.56
    发表于
    -0.51
    uglify
    -0.50
    /**
    -0.47
    Schedulers
    -0.45
     PIA
    -0.45
    diger
    -0.45
    hoof
    -0.45
     useAuth
    -0.45
    Collegamenti
    -0.44
    POSITIVE LOGITS
     Normdatei
    0.76
     jspb
    0.59
    atiche
    0.58
    結果は
    0.56
    DoubleQuotes
    0.55
     ecclesias
    0.54
     alcanzó
    0.54
    signol
    0.53
     оказалось
    0.53
     allemaal
    0.53
    Activations Density 1.628%

    No Known Activations