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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 3598
    Prev
    Next
    INDEX
    Explanations

    descriptors of easy and attractive job opportunities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    -0.54
    fromnode
    -0.52
    IsContent
    -0.52
    findpost
    -0.49
    lccn
    -0.47
     يتيمه
    -0.47
    tanleria
    -0.47
     ProtoMessage
    -0.47
    AndEndTag
    -0.46
    HtmlAttribute
    -0.46
    POSITIVE LOGITS
     aDecoder
    0.45
     tarto
    0.42
    примеча
    0.42
    amazing
    0.40
    Amazing
    0.39
    GOOD
    0.38
     LOTS
    0.38
    ↑
    0.37
     VERY
    0.37
     fantastic
    0.37
    Activations Density 0.011%

    No Known Activations