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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 69323
    Prev
    Next
    INDEX
    Explanations

    terms related to blood circulation and flow characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    AddTagHelper
    -0.73
    intios
    -0.58
    unteer
    -0.54
    lorette
    -0.52
    RegressionTest
    -0.52
     角
    -0.52
    inosa
    -0.50
    ManagedBean
    -0.50
    peza
    -0.49
    doria
    -0.49
    POSITIVE LOGITS
     circulation
    0.56
     circulatory
    0.54
     blood
    0.51
     circulación
    0.49
     Blood
    0.46
    血
    0.45
     sangre
    0.44
     الدم
    0.43
     Circulation
    0.43
    circulation
    0.43
    Activations Density 0.045%

    No Known Activations