Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 2613
    Prev
    Next
    INDEX
    Explanations

    terms related to blood and its various aspects or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paragon
    -0.78
    ExtendWith
    -0.74
     CAI
    -0.73
     chimneys
    -0.73
     Rejo
    -0.73
     Wiese
    -0.73
     paws
    -0.72
     Gabri
    -0.71
     Emilie
    -0.71
     Kett
    -0.70
    POSITIVE LOGITS
     blood
    1.43
     Blood
    1.42
     BLOOD
    1.35
    blood
    1.34
    BLOOD
    1.31
    Blood
    1.31
     Blut
    1.18
     sangre
    1.09
    的血
    1.05
     blod
    1.04
    Activations Density 0.147%

    No Known Activations