© 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. 5-GEMMASCOPE-RES-16K
    11. 6322
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to cryptography, certificates, and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esgue
    -0.83
     للاسماء
    -0.76
    ConstraintMaker
    -0.72
     kaarangay
    -0.68
     betweenstory
    -0.68
     OFDb
    -0.61
    ⟬
    -0.60
     Signalez
    -0.59
    MigrationBuilder
    -0.59
     RISERVATA
    -0.58
    POSITIVE LOGITS
    URLException
    0.61
    forName
    0.58
     vig
    0.57
     firebaseConfig
    0.56
     dotenv
    0.55
     itemView
    0.53
    basicConfig
    0.53
    Binds
    0.53
    BeginContext
    0.52
    LayoutInflater
    0.49
    Activations Density 0.482%

    No Known Activations