© 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. 11876
    Prev
    Next
    INDEX
    Explanations

    details related to programming and software development

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

    Code, punctuation, and uncommon words

    np_acts-logits-general · gemini-2.0-flash

    bracketed code syntax

    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
    -0.81
     Италијани
    -0.75
     Réponses
    -0.71
     Italijani
    -0.71
    findpost
    -0.70
    OrNil
    -0.68
    TestBed
    -0.67
    principalColumn
    -0.67
    FontOfSize
    -0.66
     OFDb
    -0.65
    POSITIVE LOGITS
     PhpStorm
    0.56
    noinspection
    0.48
     iVar
    0.47
     abbastanza
    0.46
    exels
    0.44
    Sinopse
    0.44
    hora
    0.44
     लेकर
    0.43
    stateMutability
    0.42
     policiales
    0.41
    Activations Density 0.031%

    No Known Activations