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. 12681
    Prev
    Next
    INDEX
    Explanations

    references to educational resources and tutorials related to electronics

    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
    RegressionTest
    -0.75
    ItemBackground
    -0.69
    levance
    -0.57
    Erfolge
    -0.55
    blauch
    -0.55
     nahilalakip
    -0.54
    Rujuakan
    -0.54
     blacklist
    -0.53
    VIAF
    -0.52
    Coverage
    -0.51
    POSITIVE LOGITS
     tinkering
    1.10
     DIY
    1.09
     prototyping
    1.07
     tinker
    1.03
     engineering
    1.03
    DIY
    0.96
     robotics
    0.92
     STEM
    0.91
     fabrication
    0.91
     construction
    0.89
    Activations Density 0.430%

    No Known Activations