© 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. 20-GEMMASCOPE-RES-16K
    6. 3632
    Prev
    Next
    INDEX
    Explanations

    elements and constructs commonly used in programming interfaces, particularly related to user input and event handling

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

    GUI element creation/modification

    np_acts-logits-general · gemini-2.0-flash

    individual labels

    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
    PreferredItem
    -0.65
     Wiktionnaire
    -0.56
     ferons
    -0.55
     MotionEvent
    -0.55
    dienst
    -0.55
     doigt
    -0.54
    shank
    -0.54
     AttributeSet
    -0.53
    oplast
    -0.52
    ЙТЕ
    -0.52
    POSITIVE LOGITS
    Label
    1.04
    label
    1.00
     label
    0.97
     Label
    0.93
     labels
    0.83
    lbl
    0.81
    txt
    0.80
     Labels
    0.75
     lbl
    0.75
     LABEL
    0.74
    Activations Density 0.334%

    No Known Activations