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. 7104
    Prev
    Next
    INDEX
    Explanations

    elements related to account verification and assistance for social media platforms

    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
     Italij
    -0.61
     fevere
    -0.57
     raiſ
    -0.57
     ſche
    -0.54
    Personensuche
    -0.54
     pleaſure
    -0.54
     itſelf
    -0.53
     pouvoit
    -0.52
     NSCoder
    -0.51
     fufficient
    -0.49
    POSITIVE LOGITS
     Djokovic
    0.45
    ########.
    0.38
    okovic
    0.35
     RoutedEventArgs
    0.34
    arma
    0.34
    rvats
    0.33
    jvm
    0.33
     Bashir
    0.33
    έρα
    0.33
     iter
    0.33
    Activations Density 0.149%

    No Known Activations