© 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. 11549
    Prev
    Next
    INDEX
    Explanations

    confirmations and assertions related to specific processes or standards

    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
    EndContext
    -0.81
    :✨
    -0.77
     calendriers
    -0.77
    الحياه
    -0.73
     виправивши
    -0.73
    kuuta
    -0.68
    +#+#
    -0.67
     okuyayım
    -0.66
     validamos
    -0.66
     تانيه
    -0.65
    POSITIVE LOGITS
    <eos>
    0.64
     Особенно
    0.53
     Thus
    0.52
     However
    0.48
    idł
    0.47
    Msk
    0.47
    plätze
    0.46
    Thus
    0.46
     CWE
    0.45
     Thereafter
    0.45
    Activations Density 0.591%

    No Known Activations