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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2665
    Prev
    Next
    INDEX
    Explanations

    phrases related to cardiac conditions and treatments

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

    preceding "treatment"

    np_acts-logits-general · gemini-2.0-flash

    medical treatment and therapy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esternos
    -0.56
    risten
    -0.47
     Belmont
    -0.46
    OOTDTY
    -0.46
     revend
    -0.45
    MigrationBuilder
    -0.45
     aufgestellt
    -0.44
    devamını
    -0.44
    inerja
    -0.44
    bilt
    -0.44
    POSITIVE LOGITS
     treatment
    2.20
     Treatment
    1.87
    treatment
    1.84
     treat
    1.79
    Treatment
    1.78
     TREATMENT
    1.71
    treat
    1.67
     treating
    1.67
     treatments
    1.65
     treated
    1.64
    Activations Density 1.363%

    No Known Activations