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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7522
    Prev
    Next
    INDEX
    Explanations

    names of researchers and collaborators in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
    webElementXpaths
    -0.80
     ſche
    -0.77
     Monfieur
    -0.76
    AccessorTable
    -0.74
     lenker
    -0.74
     ſont
    -0.73
     étoient
    -0.73
    rungsseite
    -0.72
    ſehen
    -0.72
    :✨
    -0.70
    POSITIVE LOGITS
     Portugal
    0.50
    Portugal
    0.44
    Bissau
    0.40
     Portuguese
    0.37
    Portuguese
    0.34
    ,
    0.33
     Aberdeen
    0.31
    jedis
    0.30
     portugal
    0.29
     说明
    0.29
    Activations Density 0.074%

    No Known Activations