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. 10-GEMMASCOPE-RES-16K
    6. 11836
    Prev
    Next
    INDEX
    Explanations

    terms associated with organ conditions and medical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ../../
    -0.95
    ../../../
    -0.91
    alike
    -0.86
    cody
    -0.83
     Knox
    -0.81
    ogeneity
    -0.80
    Benson
    -0.79
    ULTY
    -0.79
    ่น
    -0.78
     Montagne
    -0.78
    POSITIVE LOGITS
     Ir
    1.47
    ir
    1.45
    Ir
    1.35
    IR
    1.33
     CIR
    1.26
    nir
    1.17
     IR
    1.17
     Jir
    1.15
    tir
    1.13
    hir
    1.13
    Activations Density 0.231%

    No Known Activations