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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5238
    Prev
    Next
    INDEX
    Explanations

    medical terms and conditions related to vascular and blood flow issues

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

    blood vessels and microvasculature

    np_acts-logits-general · gemini-2.0-flash

    vascular structures and their growth

    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
    βο
    -0.49
    Istorija
    -0.42
     atheist
    -0.42
     FTX
    -0.40
     Enc
    -0.39
     rape
    -0.39
     rũ
    -0.38
    щина
    -0.38
    ATK
    -0.38
     amare
    -0.38
    POSITIVE LOGITS
     vessels
    1.22
     vessel
    1.16
     Vessels
    1.15
     Vessel
    1.12
    Vessel
    1.08
     blood
    1.07
     arteries
    1.07
     vascular
    1.06
    vessel
    1.05
     vas
    1.04
    Activations Density 0.827%

    No Known Activations