© 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. 14-GEMMASCOPE-RES-16K
    11. 398
    Prev
    Next
    INDEX
    Explanations

    phrases indicating associations or combinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Empieza
    -0.52
    S
    -0.52
     порядке
    -0.51
    EndContext
    -0.51
    kkor
    -0.51
    C
    -0.50
     SEDS
    -0.48
     mesmas
    -0.47
    脚注の使い方
    -0.47
    StructEnd
    -0.46
    POSITIVE LOGITS
     accompanying
    0.76
     concomitant
    0.72
     other
    0.72
    makeText
    0.70
     complemented
    0.70
     Paglinawan
    0.67
    pogon
    0.67
     accompanied
    0.66
     others
    0.64
     complements
    0.64
    Activations Density 0.351%

    No Known Activations