© 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. 13330
    Prev
    Next
    INDEX
    Explanations

    terms related to direct actions or direct processes

    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
    hbs
    -0.69
    modelBuilder
    -0.62
     Donnie
    -0.61
     Bute
    -0.61
     mẫu
    -0.60
    accumulative
    -0.60
    byte
    -0.59
     Kond
    -0.59
    ر
    -0.58
    ngdoc
    -0.58
    POSITIVE LOGITS
     directly
    1.99
    directly
    1.99
     Directly
    1.81
     directement
    1.52
     directamente
    1.43
     diretamente
    1.31
     direttamente
    1.24
     bezpośrednio
    1.22
     indirectly
    1.17
     trực
    1.13
    Activations Density 0.114%

    No Known Activations