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. 1613
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and conjunctions that express dependencies in statements

    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
     alternativo
    -0.38
    ,
    -0.36
    /
    -0.32
     quarto
    -0.31
     correspon
    -0.31
     alternative
    -0.30
     запла
    -0.30
     uniform
    -0.29
     Taliban
    -0.29
     reader
    -0.29
    POSITIVE LOGITS
     برانيه
    0.84
    InitVars
    0.79
     Infórmanos
    0.74
     Мексичка
    0.73
     насељу
    0.71
    RefNanny
    0.70
    iſen
    0.68
    rungsseite
    0.67
     Numerade
    0.66
    Personendaten
    0.66
    Activations Density 0.618%

    No Known Activations