© 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. 15120
    Prev
    Next
    INDEX
    Explanations

    informal expressions or phrases indicating condition or reason

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

    Archaic or shortened conjunctions/adverbs

    np_acts-logits-general · gemini-2.0-flash

    conjunctions or subordinate clauses

    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
    +#+#
    -1.09
    ImageContext
    -0.94
     EconPapers
    -0.94
    enumi
    -0.88
    AsUp
    -0.85
    ThemeOverlay
    -0.77
    WithIOException
    -0.77
     المعيارى
    -0.76
    kannya
    -0.76
    OGND
    -0.73
    POSITIVE LOGITS
    quele
    0.93
    gether
    0.93
    theless
    0.68
    forth
    0.67
    haupt
    0.65
    selben
    0.62
    orexia
    0.60
    sertation
    0.59
    ある
    0.59
    oretical
    0.59
    Activations Density 0.608%

    No Known Activations