© 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. 4-GEMMASCOPE-RES-16K
    6. 2300
    Prev
    Next
    INDEX
    Explanations

    references to blood and its related metrics or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    例句
    -0.94
     Athe
    -0.80
     trimester
    -0.76
     Gabri
    -0.76
     Esau
    -0.75
     Villas
    -0.74
     Reggio
    -0.73
    DialogInterface
    -0.73
    ClientSize
    -0.73
     atheism
    -0.73
    POSITIVE LOGITS
     blood
    2.76
     Blood
    2.64
    Blood
    2.54
    blood
    2.51
     BLOOD
    2.46
    BLOOD
    2.29
     blod
    1.80
     Blut
    1.80
    血
    1.79
     sangre
    1.73
    Activations Density 0.048%

    No Known Activations