© 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. 541
    Prev
    Next
    INDEX
    Explanations

    elements of a programming language's syntax, particularly related to data structures and definitions

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

    "string" or "optional"

    np_acts-logits-general · gemini-2.0-flash

    support or optional strings

    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
    devtools
    -0.43
    jws
    -0.39
    klo
    -0.38
     Academy
    -0.38
    skapet
    -0.38
    DEV
    -0.37
     Paw
    -0.37
    mede
    -0.37
    seat
    -0.37
    Pyx
    -0.37
    POSITIVE LOGITS
     string
    1.48
    String
    1.43
     String
    1.43
     Stringer
    1.40
    string
    1.39
    STRING
    1.30
     STRING
    1.28
     strings
    1.23
     Strings
    1.15
    tring
    1.09
    Activations Density 0.111%

    No Known Activations