Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3225
    Prev
    Next
    INDEX
    Explanations

    elements related to programming functions, plugins, and filtering processes

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

    "ignoreversion" flag in Inno Setup scripts

    np_acts-logits-general · gemini-2.0-flash

    ignore version

    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
     EconPapers
    -1.34
    SequentialGroup
    -1.09
     AssemblyCulture
    -1.04
     nakalista
    -1.04
     doubtnut
    -0.99
    amaño
    -0.99
    tvguidetime
    -0.98
     ThemeData
    -0.97
     الحره
    -0.95
    SourceChecksum
    -0.94
    POSITIVE LOGITS
    _
    0.65
    omy
    0.54
     _
    0.52
    …
    0.51
    </em>
    0.51
    oned
    0.51
     Kreis
    0.49
     single
    0.49
     non
    0.48
    ulating
    0.47
    Activations Density 0.256%

    No Known Activations