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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-GEMMASCOPE-RES-16K
    6. 12811
    Prev
    Next
    INDEX
    Explanations

    references to components and classes related to programming frameworks or libraries

    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
     onCreate
    -0.86
    Pyx
    -0.82
    neux
    -0.58
     ens
    -0.57
    _));
    -0.54
    ปร
    -0.53
    Threading
    -0.53
    ﻣ
    -0.52
    rxjs
    -0.52
     mula
    -0.51
    POSITIVE LOGITS
    loader
    1.01
    awtextra
    0.89
    IsContent
    0.88
    addCriterion
    0.80
     loader
    0.79
    RuleContext
    0.78
    principalColumn
    0.78
    Loader
    0.77
    @[+][
    0.76
    BeginContext
    0.76
    Activations Density 0.014%

    No Known Activations