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. 20-GEMMASCOPE-RES-16K
    6. 11037
    Prev
    Next
    INDEX
    Explanations

    phrases related to legends and mythical elements

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

    Text after commas or articles

    np_acts-logits-general · gemini-2.0-flash

    cultivation words

    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-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
    tagHelperRunner
    -0.71
    AccessorTable
    -0.56
    parsedMessage
    -0.55
    MLLoader
    -0.54
     <=",
    -0.52
    IntoConstraints
    -0.50
     transfieras
    -0.50
     zast
    -0.49
    UnsafeEnabled
    -0.48
     beginnetje
    -0.48
    POSITIVE LOGITS
     cultivation
    0.96
     cultivators
    0.84
     cultivator
    0.84
     refining
    0.81
     Cultivation
    0.79
     Dao
    0.76
     cultivating
    0.73
     cultiv
    0.73
    culti
    0.73
    Culti
    0.70
    Activations Density 0.065%

    No Known Activations