Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7235
    Prev
    Next
    INDEX
    Explanations

    titles and honors of individuals

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

    Titles, honorifics, and post-nominal letters

    np_acts-logits-general · gemini-2.0-flash

    academic degrees and professional titles

    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
    RenderAtEndOf
    -0.74
    WithIOException
    -0.73
     فريبيس
    -0.69
    ]")]
    -0.68
    Autoritní
    -0.67
    الحياه
    -0.66
    Personensuche
    -0.66
     незавершена
    -0.66
     referenties
    -0.65
     وتسجيلات
    -0.65
    POSITIVE LOGITS
     PhD
    0.82
     Esq
    0.78
     BSc
    0.72
    PhD
    0.72
     Esquire
    0.70
     M
    0.69
     MBA
    0.69
     MSc
    0.68
     CBE
    0.66
     MBE
    0.66
    Activations Density 0.177%

    No Known Activations