© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 10924
    Prev
    Next
    INDEX
    Explanations

    terms related to vascular dynamics and hypoxia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     оригіналу
    -0.41
    JspWriter
    -0.38
     houſe
    -0.37
    ьаж
    -0.37
    interopRequire
    -0.36
     faſt
    -0.35
     techo
    -0.35
    TestingModule
    -0.35
    Kontrola
    -0.35
     AssemblyTitle
    -0.35
    POSITIVE LOGITS
     vessels
    1.16
     vessel
    1.15
     vascular
    1.14
     veins
    1.10
     Vascular
    1.09
     arteries
    1.08
     Vessel
    1.07
     Vessels
    1.05
     vein
    1.05
     artery
    1.04
    Activations Density 0.824%

    No Known Activations