© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 8444
    Prev
    Next
    INDEX
    Explanations

    quantitative descriptions and ratios in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.55
     Jinping
    -0.51
     defaultstate
    -0.48
    ۣ
    -0.42
     beha
    -0.40
     CURIAM
    -0.40
    ihnachten
    -0.39
    hbase
    -0.39
    存于互联网档案馆
    -0.39
    simpleType
    -0.38
    POSITIVE LOGITS
    出版年
    0.78
     Ratio
    0.75
     Ratios
    0.74
     ratios
    0.72
    SizeF
    0.72
     surla
    0.71
    +:+
    0.69
    tanleria
    0.68
    %)$
    0.67
    /******/
    0.66
    Activations Density 1.053%

    No Known Activations