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. 21-GEMMASCOPE-RES-16K
    6. 8329
    Prev
    Next
    INDEX
    Explanations

    references to acute lymphoblastic leukemia and related medical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     McCormack
    -0.50
    athread
    -0.48
     Dickerson
    -0.47
    irci
    -0.47
     McCormick
    -0.45
     Gustavo
    -0.45
     Pingback
    -0.45
     Duckworth
    -0.44
    Gustavo
    -0.44
     Adnan
    -0.44
    POSITIVE LOGITS
    ell
    0.73
     QL
    0.72
    el
    0.70
    rell
    0.69
    ral
    0.69
    oll
    0.68
    all
    0.68
    del
    0.68
     RAL
    0.68
    tel
    0.68
    Activations Density 0.642%

    No Known Activations