© 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. 3810
    Prev
    Next
    INDEX
    Explanations

    mathematical or programming expressions and structures

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

    Code or data snippets

    np_acts-logits-general · gemini-2.0-flash

    e.g. plugin, subsequently, gas

    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
     I
    -1.15
     y
    -1.09
     A
    -1.08
     de
    -1.04
     l
    -1.03
     M
    -1.03
     van
    -1.02
     i
    -1.02
     di
    -1.02
     V
    -1.01
    POSITIVE LOGITS
     itſelf
    2.28
     myſelf
    2.00
     pleaſure
    1.95
     Monfieur
    1.90
     Reſ
    1.89
     poffible
    1.87
     Diſ
    1.85
     ſeveral
    1.84
     raiſ
    1.82
     greateſt
    1.81
    Activations Density 1.008%

    No Known Activations