© 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. 4-GEMMASCOPE-RES-16K
    11. 10510
    Prev
    Next
    INDEX
    Explanations

    phrases indicating problems or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    旧
    -0.61
     població
    -0.59
    LookAnd
    -0.58
    舊
    -0.54
    
    -0.52
    foria
    -0.49
    paedia
    -0.47
    isement
    -0.47
    strat
    -0.47
     avut
    -0.45
    POSITIVE LOGITS
    RegressionTest
    0.80
    ########.
    0.69
    RectangleBorder
    0.67
    __':
    0.65
    ętr
    0.63
    !("{}",
    0.63
     Wraith
    0.63
     Cotter
    0.63
    ChildScrollView
    0.63
    sqcup
    0.62
    Activations Density 0.636%

    No Known Activations