© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7115
    Prev
    Next
    INDEX
    Explanations

    terms related to brain tumors and their treatment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after mentions of "brain"

    np_acts-logits-general · gemini-2.0-flash

    brain diseases and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -0.67
    flashdata
    -0.54
    parametrize
    -0.51
     Hose
    -0.50
     Antwerpen
    -0.50
     RoutedEventArgs
    -0.49
    phage
    -0.49
    DRAG
    -0.49
     shortness
    -0.48
     Tompkins
    -0.48
    POSITIVE LOGITS
     brain
    1.57
     Brain
    1.41
     brains
    1.36
    brain
    1.36
    Brain
    1.35
     neuro
    1.32
     Neuro
    1.18
     BRAIN
    1.18
     cerebral
    1.18
     Brains
    1.16
    Activations Density 1.243%

    No Known Activations