© 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. 17-GEMMASCOPE-RES-16K
    11. 2040
    Prev
    Next
    INDEX
    Explanations

    technical terms and descriptors that imply complexity or simplicity in processes or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     détru
    -0.52
     déliv
    -0.52
     særlig
    -0.51
     sī
    -0.51
    zuli
    -0.50
    +#+#
    -0.49
    ươi
    -0.48
     arrêté
    -0.48
     विश्वसनीयता
    -0.48
     enregistré
    -0.47
    POSITIVE LOGITS
     yet
    0.95
    yet
    0.85
    theless
    0.79
    WebVitals
    0.75
    StructEnd
    0.74
    ๆ
    0.74
    ̈́
    0.72
    ながらも
    0.71
     gehalten
    0.71
     minded
    0.71
    Activations Density 0.383%

    No Known Activations