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. 19-GEMMASCOPE-RES-16K
    6. 2052
    Prev
    Next
    INDEX
    Explanations

    terms related to "development."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lucene
    -0.61
     épar
    -0.60
    legion
    -0.60
    uarts
    -0.55
    abuse
    -0.52
    zaken
    -0.51
    ukary
    -0.51
    aceae
    -0.51
     scor
    -0.51
    judic
    -0.51
    POSITIVE LOGITS
    Datuak
    0.80
    pement
    0.72
    Develop
    0.68
    twimg
    0.66
    ")){
    
    0.64
     ADM
    0.61
     developers
    0.61
    develop
    0.61
    DEVELOPMENT
    0.60
     Devonshire
    0.60
    Activations Density 0.139%

    No Known Activations