© 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. 7857
    Prev
    Next
    INDEX
    Explanations

    references to particle physics experiments and constraints on theoretical models

    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
     “
    -0.47
     track
    -0.46
    BatchNorm
    -0.43
    /
    -0.40
    ↵↵
    -0.40
    <eos>
    -0.40
    ייל
    -0.39
    GetEnumerator
    -0.39
    .”
    -0.39
    Read
    -0.38
    POSITIVE LOGITS
    oredCriteria
    0.79
    Personendaten
    0.79
    TestingModule
    0.79
     Мексичка
    0.78
    ագրություններ
    0.77
    KommentareTeilen
    0.77
     intptr
    0.74
     CreateTagHelper
    0.73
    homonymie
    0.73
    enumi
    0.72
    Activations Density 2.443%

    No Known Activations