Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 14172
    Prev
    Next
    INDEX
    Explanations

    instances of the word "simple" and related descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/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.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IBarButtonItem
    -0.97
     atteinte
    -0.88
     debout
    -0.84
     passim
    -0.82
     voici
    -0.81
     perpétu
    -0.80
     polaire
    -0.80
    labelledby
    -0.79
     artesanales
    -0.79
     avoient
    -0.79
    POSITIVE LOGITS
     SIMPLE
    1.28
     Simple
    1.25
     simple
    1.20
    Simple
    1.12
    SIMPLE
    1.11
    simple
    1.00
     simpl
    0.97
     simples
    0.96
    simpleType
    0.91
     Plain
    0.90
    Activations Density 0.078%

    No Known Activations