© 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. 1119
    Prev
    Next
    INDEX
    Explanations

    references to the Protobuf framework and related elements in programming

    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
    WriteTagHelper
    -0.91
    UrlResolution
    -0.58
    addContainerGap
    -0.55
     Enkel
    -0.52
     Marcin
    -0.47
     successors
    -0.46
     impré
    -0.46
     adverbs
    -0.45
     mecán
    -0.45
     zufolge
    -0.45
    POSITIVE LOGITS
    enumi
    1.56
    protobuf
    1.02
    jgl
    0.94
    WEBPACK
    0.94
    __':
    0.92
     UnityEngine
    0.88
    Datuak
    0.80
    __':
    0.79
    enumii
    0.76
    ynb
    0.73
    Activations Density 0.014%

    No Known Activations