© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5349
    Prev
    Next
    INDEX
    Explanations

    patterns or structures related to programming or code organization

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

    Code snippets and special characters

    np_acts-logits-general · gemini-2.0-flash

    programming code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     off
    -0.58
    MigrationBuilder
    -0.55
     lụa
    -0.54
    Życiorys
    -0.54
    ̀u
    -0.53
     gra
    -0.53
     ElementRef
    -0.53
     Brow
    -0.53
     street
    -0.52
     AB
    -0.52
    POSITIVE LOGITS
     مشين
    0.81
     itſelf
    0.71
     insuffisamment
    0.66
    uxxxx
    0.64
     kasarigan
    0.62
     ་་
    0.61
     poffible
    0.60
     незавершена
    0.60
    InputBorder
    0.60
     fufficient
    0.58
    Activations Density 0.045%

    No Known Activations