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. 4655
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to cosmetic procedures and patient experiences

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

    Significant improvement

    np_acts-logits-general · gemini-2.0-flash

    positive outcomes

    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
    しまいます
    -0.61
    NameInMap
    -0.58
    lwjgl
    -0.55
    HasIndex
    -0.53
    migrationBuilder
    -0.53
    AndroidJUnit
    -0.53
    Décès
    -0.51
    HasAnnotation
    -0.51
    unless
    -0.51
    المناصب
    -0.49
    POSITIVE LOGITS
     improvement
    1.29
     improved
    1.28
     improvements
    1.25
    improved
    1.10
     Improvements
    1.10
     Improved
    1.08
     Improvement
    1.07
    Improved
    1.05
    Improvement
    1.03
    Improvements
    1.01
    Activations Density 0.445%

    No Known Activations