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. 25-GEMMASCOPE-RES-16K
    6. 6004
    Prev
    Next
    INDEX
    Explanations

    terms related to cardiology and heart conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.67
    UserScript
    -0.63
    UnsafeEnabled
    -0.60
    multirow
    -0.59
    ScopeManager
    -0.58
    ặt
    -0.53
    AddHtmlAttribute
    -0.52
     ISNI
    -0.50
     NgModule
    -0.50
    rawDesc
    -0.50
    POSITIVE LOGITS
     heart
    1.72
     Heart
    1.59
    Heart
    1.54
    heart
    1.52
     cardiac
    1.51
     Cardiac
    1.40
     HEART
    1.39
     coronary
    1.34
     myocardial
    1.34
     hearts
    1.33
    Activations Density 1.362%

    No Known Activations