© 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-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 15252
    Prev
    Next
    INDEX
    Explanations

    terms related to cardiac conditions and treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rab
    -0.58
    lat
    -0.57
    لي
    -0.56
    ok
    -0.56
    por
    -0.55
    pen
    -0.55
    lad
    -0.54
    미
    -0.54
    ро
    -0.54
    sim
    -0.53
    POSITIVE LOGITS
    Diweddarwch
    1.23
    tonsoft
    1.19
    __':
    
    1.16
     Италијани
    1.15
    verwijspagina
    1.15
     OFDb
    1.11
    ChildScrollView
    1.10
    vician
    1.10
     للاسماء
    1.08
    __":
    
    1.08
    Activations Density 2.788%

    No Known Activations