Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 8549
    Prev
    Next
    INDEX
    Explanations

    keywords related to historical influences and legacy

    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
     للاسماء
    -0.82
    IsContent
    -0.69
    mobileqq
    -0.65
     nahilalakip
    -0.64
    الحياه
    -0.58
     titolata
    -0.56
    Datuak
    -0.56
    marshaller
    -0.56
     propOrder
    -0.55
     isInitialized
    -0.55
    POSITIVE LOGITS
     footprints
    1.60
     traces
    1.59
     footprint
    1.55
     imprint
    1.52
     mark
    1.51
     Spuren
    1.50
     marks
    1.44
     trace
    1.42
     Traces
    1.27
     huella
    1.25
    Activations Density 0.360%

    No Known Activations