© 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. 10439
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software development, particularly in Java and its libraries

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

    After periods followed by "commons" or "cl" or "felix"

    np_acts-logits-general · gemini-2.0-flash

    org.apache.commons

    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
     الاطلاع
    -0.56
     omt
    -0.54
    VersionUID
    -0.53
    MenuView
    -0.53
    wäsche
    -0.52
    Getenv
    -0.51
    الإنجليزية
    -0.50
     toegang
    -0.50
     internazionali
    -0.48
    destroyAll
    -0.46
    POSITIVE LOGITS
    PyExc
    0.64
     Trig
    0.59
    OrNil
    0.59
    "]="
    0.58
     useAuth
    0.57
    ">/
    0.57
    ']='
    0.56
    ">:
    0.56
    psack
    0.56
    lads
    0.55
    Activations Density 0.077%

    No Known Activations