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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 784
    Prev
    Next
    INDEX
    Explanations

    concepts related to cell cycle regulation and proliferation mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    scientific terms related to cell biology and cellular mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    cell cycle and mitosis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    findpost
    -0.56
     Monats
    -0.55
    strix
    -0.49
     jaar
    -0.47
     złoż
    -0.43
     výro
    -0.43
     مرئيه
    -0.43
    CreateModel
    -0.42
    SnackBar
    -0.42
     esclu
    -0.42
    POSITIVE LOGITS
     mitotic
    0.99
     mitosis
    0.99
     cell
    0.76
     arrested
    0.74
     replication
    0.71
     phase
    0.70
     Phase
    0.68
     cytok
    0.68
     arrest
    0.68
    PHASE
    0.67
    Activations Density 0.375%

    No Known Activations