© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5995
    Prev
    Next
    INDEX
    Explanations

    numerical values and their representations within a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 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
    rungsseite
    -1.02
     विश्वसनीयता
    -0.87
     Geſ
    -0.70
    lapsingToolbar
    -0.69
     Monfieur
    -0.68
     EconPapers
    -0.65
     يتيمه
    -0.65
    ulongan
    -0.65
    BagConstraints
    -0.63
     Theſe
    -0.62
    POSITIVE LOGITS
     en
    0.27
     
    0.27
    runApp
    0.26
     I
    0.26
    oph
    0.25
    wer
    0.25
    en
    0.25
    are
    0.24
     procu
    0.24
    os
    0.24
    Activations Density 0.489%

    No Known Activations