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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 4997
    Prev
    Next
    INDEX
    Explanations

    dates, specifically in the month of September

    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
    帖最后由
    -0.55
    UnifiedTopology
    -0.49
    Portale
    -0.48
     Jan
    -0.47
     Win
    -0.46
     Tal
    -0.45
     dim
    -0.45
    enterOuterAlt
    -0.45
     trade
    -0.45
    akad
    -0.45
    POSITIVE LOGITS
    SEPTEMBER
    0.83
    ftagPool
    0.79
    tembre
    0.78
     SEP
    0.77
     SEPTEMBER
    0.76
     Hermitage
    0.76
    entri
    0.75
     myſelf
    0.74
    September
    0.73
     Monfieur
    0.72
    Activations Density 0.040%

    No Known Activations