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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 902
    Prev
    Next
    INDEX
    Explanations

    references to specific companies and laboratories involved in medical and scientific research

    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
     Capital
    -0.53
    pace
    -0.50
    runOnUiThread
    -0.48
     shop
    -0.48
    createTextNode
    -0.48
     capital
    -0.48
    ysen
    -0.47
     area
    -0.46
    遇
    -0.45
     local
    -0.45
    POSITIVE LOGITS
     CreateTagHelper
    0.82
    writeFieldEnd
    0.69
    \{\\
    0.68
    SequentialGroup
    0.67
    WithIOException
    0.64
    RegistryLite
    0.62
    featureID
    0.59
    LANTA
    0.58
     Efq
    0.58
    出版年
    0.56
    Activations Density 0.204%

    No Known Activations