© 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. 3-GEMMASCOPE-RES-16K
    6. 13572
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly those indicating significant amounts or results, often in legal or financial contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.66
    Последние
    -0.65
     InputDecoration
    -0.61
    lujah
    -0.60
     Chord
    -0.59
    ://$
    -0.58
    saraba
    -0.58
    Normdaten
    -0.58
    matchCondition
    -0.57
     كومونز
    -0.57
    POSITIVE LOGITS
     year
    0.88
    年
    0.86
     jaar
    0.75
     years
    0.74
    year
    0.72
     Year
    0.72
    ⓧ
    0.69
    getYear
    0.69
    년
    0.68
     Jahr
    0.67
    Activations Density 0.347%

    No Known Activations