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. 11800
    Prev
    Next
    INDEX
    Explanations

    specific terms and acronyms related to biological and medical research

    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
    міністра
    -0.66
    DeclareMath
    -0.58
    Carrera
    -0.57
     The
    -0.57
    #\
    -0.57
     A
    -0.57
    rxjs
    -0.56
    paddingVertical
    -0.55
    flü
    -0.55
    marginLeft
    -0.55
    POSITIVE LOGITS
     bof
    1.10
     Jod
    1.09
     SOT
    1.06
     Fod
    1.02
    AOC
    1.02
     Socorro
    1.00
     Sox
    1.00
     AOC
    0.99
     Wod
    0.98
     FOS
    0.95
    Activations Density 1.715%

    No Known Activations