© 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. 9315
    Prev
    Next
    INDEX
    Explanations

    various forms of currency symbols and their associated signs

    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
     
    -0.82
    A
    -0.78
    e
    -0.75
    P
    -0.71
    E
    -0.70
    <eos>
    -0.70
     (
    -0.70
    ↵
    -0.69
    C
    -0.68
    K
    -0.68
    POSITIVE LOGITS
     Jefus
    1.71
     myſelf
    1.68
     raiſ
    1.52
     faſt
    1.50
     Monfieur
    1.49
     itſelf
    1.47
     ſeveral
    1.46
     ſta
    1.43
     iſt
    1.43
     pleaſure
    1.43
    Activations Density 0.499%

    No Known Activations