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. 15712
    Prev
    Next
    INDEX
    Explanations

    phrases related to cerebral blood flow and its dynamics in various physiological states

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

    Blood flow or circulation

    np_acts-logits-general · gemini-2.0-flash

    blood flow and circulation

    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
    ⓧ
    -0.67
     initComponents
    -0.66
    RegressionTest
    -0.64
    \{\\
    -0.58
     Baillargeon
    -0.57
     TextAppearance
    -0.56
    igshid
    -0.56
    UnitTesting
    -0.55
     CreateTagHelper
    -0.54
     ashore
    -0.54
    POSITIVE LOGITS
     flow
    1.91
    flow
    1.59
     Flow
    1.57
     flows
    1.51
    Flow
    1.50
     FLOW
    1.44
     Flows
    1.33
     circulation
    1.33
     flowing
    1.31
     flujo
    1.30
    Activations Density 0.386%

    No Known Activations