© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 8-GEMMASCOPE-RES-16K
    11. 410
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "prototype" in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    us
    -0.68
    was
    -0.65
    is
    -0.64
     in
    -0.64
    l
    -0.62
    or
    -0.62
    {
    -0.60
    put
    -0.60
     on
    -0.59
    r
    -0.58
    POSITIVE LOGITS
    prototype
    2.44
     Prototype
    1.55
     prototype
    1.48
     prototypes
    1.47
    Prototype
    1.42
     prototyping
    1.10
    OrBuilder
    1.10
    PrototypeOf
    1.09
     nahilalakip
    1.08
     MainAxisSize
    1.07
    Activations Density 0.028%

    No Known Activations