© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 15002
    Prev
    Next
    INDEX
    Explanations

    terms related to neural network performance metrics and architectures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.59
     للاسماء
    -0.59
    roek
    -0.58
    orianCalendar
    -0.55
     espirituales
    -0.52
     reunião
    -0.50
     Brice
    -0.50
     AssemblyVersion
    -0.48
     liderança
    -0.48
    tổng
    -0.48
    POSITIVE LOGITS
     training
    1.55
     trained
    1.35
    Training
    1.25
    training
    1.25
     Training
    1.24
     TRAINING
    1.15
    trained
    1.12
     train
    1.08
    train
    1.06
    TRAINING
    1.05
    Activations Density 1.867%

    No Known Activations