© 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. 3-GEMMASCOPE-RES-16K
    11. 9683
    Prev
    Next
    INDEX
    Explanations

    commands and functions related to JSON data encoding and decoding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
    WaitGroup
    -0.79
     betweenstory
    -0.77
     myſelf
    -0.76
     Monfieur
    -0.70
     ModelExpression
    -0.69
     Majefty
    -0.66
     Huguen
    -0.65
     initComponents
    -0.65
     pleaſure
    -0.65
    wiſe
    -0.63
    POSITIVE LOGITS
    JSONException
    0.69
    📻
    0.55
    BASELINE
    0.53
    ้ว
    0.52
     préférences
    0.51
    CheckedChanged
    0.51
    rubin
    0.51
     grunn
    0.50
    pretation
    0.49
    stringify
    0.48
    Activations Density 0.142%

    No Known Activations