© 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. 1340
    Prev
    Next
    INDEX
    Explanations

    information related to film awards and nominations

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

    Follows punctuation or quotes

    np_acts-logits-general · gemini-2.0-flash

    movies and celebrities

    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
    ReusableCell
    -0.89
    PerformLayout
    -0.77
    UnknownFieldSet
    -0.77
    odeon
    -0.75
     Baillargeon
    -0.75
    tagHelperRunner
    -0.73
     समीक्षाएं
    -0.69
    +#+#
    -0.69
    UnitTesting
    -0.68
     Meksiku
    -0.67
    POSITIVE LOGITS
    Vanjske
    0.47
    nmgp
    0.46
    setEditable
    0.44
    blij
    0.39
    tagext
    0.38
    à
    0.38
    נש
    0.38
    cial
    0.36
    กก
    0.36
    cese
    0.35
    Activations Density 0.217%

    No Known Activations