© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 699
    Prev
    Next
    INDEX
    Explanations

    references to healthcare and related regulatory programmes

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

    "programme" or "haemoglobin"

    np_acts-logits-general · gemini-2.0-flash

    programme or programmes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     Harbor
    -0.55
     Savior
    -0.54
    ency
    -0.54
     czar
    -0.53
     Stacy
    -0.53
    اً
    -0.52
     mustache
    -0.52
     Center
    -0.52
    Stacy
    -0.51
     parlor
    -0.50
    POSITIVE LOGITS
    Programme
    0.90
     programme
    0.85
    programme
    0.85
     Programme
    0.84
     PROGRAMME
    0.83
     aeroplane
    0.80
     watercolour
    0.78
     woollen
    0.76
     programmes
    0.75
     Programmes
    0.75
    Activations Density 0.514%

    No Known Activations