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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 16280
    Prev
    Next
    INDEX
    Explanations

    references to specific genes and related biomedical terminology

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

    followed by specific suffixes

    np_acts-logits-general · gemini-2.0-flash

    words or beginnings of phrases

    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
    s
    -1.83
    y
    -1.79
    i
    -1.68
    e
    -1.53
    ه
    -1.49
    er
    -1.47
    o
    -1.45
    ی
    -1.41
    t
    -1.40
    es
    -1.32
    POSITIVE LOGITS
     Efq
    1.30
     itſelf
    1.24
     myſelf
    1.23
     Shakspeare
    1.17
     purpoſe
    1.17
     Houſe
    1.16
     themſelves
    1.15
    ſelves
    1.12
     '\\;'
    1.10
    ostante
    1.10
    Activations Density 1.668%

    No Known Activations