© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 9082
    Prev
    Next
    INDEX
    Explanations

    references to blood testing and related medical procedures

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

    blood samples or blood stream

    np_acts-logits-general · gemini-2.0-flash

    blood and circulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IonicModule
    -0.49
    pesas
    -0.47
    indd
    -0.46
    -------
    -0.46
     ***!
    -0.46
     rape
    -0.45
    },[])
    -0.45
    ntgen
    -0.44
     BoxFit
    -0.44
     sauvages
    -0.43
    POSITIVE LOGITS
     blood
    1.85
    blood
    1.60
     Blood
    1.56
     BLOOD
    1.47
    Blood
    1.47
     bloodstream
    1.34
    BLOOD
    1.30
     veins
    1.29
     sangre
    1.22
    血液
    1.22
    Activations Density 0.534%

    No Known Activations