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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-GEMMASCOPE-RES-16K
    6. 2810
    Prev
    Next
    INDEX
    Explanations

    references to cancer cells and their regulatory mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.83
     للاسماء
    -0.66
    ίδι
    -0.60
     Forumite
    -0.59
    ztály
    -0.58
    AutoScale
    -0.56
    etheless
    -0.55
    ThroughAttribute
    -0.54
    SequentialGroup
    -0.53
    elry
    -0.53
    POSITIVE LOGITS
    TypedDataSet
    0.76
    webElementGuid
    0.57
    enumi
    0.57
    ineno
    0.55
    GeneratedCode
    0.53
    BeginContext
    0.52
    fjspx
    0.52
    kuuta
    0.52
    ruik
    0.51
    TagMode
    0.50
    Activations Density 0.885%

    No Known Activations