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. 4690
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to neural mechanisms and pathways in the context of physiology and disorder

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

    Brain areas and neural circuitry

    np_acts-logits-general · gemini-2.0-flash

    brain areas and regions

    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
     tartalomajánló
    -0.58
     secco
    -0.51
     UIP
    -0.48
     trachea
    -0.48
     turg
    -0.47
     Erişim
    -0.47
     niedersachsen
    -0.46
     εφ
    -0.45
     Kommune
    -0.45
     Ouv
    -0.45
    POSITIVE LOGITS
     areas
    0.73
     regions
    0.71
     Brod
    0.69
    encodeWith
    0.69
     area
    0.67
    modb
    0.65
    Areas
    0.64
     Areas
    0.64
     Bro
    0.62
     Area
    0.61
    Activations Density 0.465%

    No Known Activations