© 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 EvalsExportsinterp-engineNEWAPI 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. 1041
    Prev
    Next
    INDEX
    Explanations

    HTML classes and styles used in web documents

    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
     aj
    -0.46
    貧
    -0.45
    divia
    -0.43
    __.__
    -0.42
     égard
    -0.41
     erw
    -0.41
    rü
    -0.41
    argue
    -0.41
     Koch
    -0.39
    otá
    -0.39
    POSITIVE LOGITS
    enumi
    1.39
    脚注の使い方
    1.28
     оригіналу
    1.21
    enumii
    1.11
    Revenir
    1.09
    tvguidetime
    1.01
     تضيفلها
    1.00
     typelib
    0.99
    BeginContext
    0.99
    istoitu
    0.99
    Activations Density 0.357%

    No Known Activations