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. 11571
    Prev
    Next
    INDEX
    Explanations

    phrases indicating public availability and community engagements

    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
     hot
    -0.33
     Hot
    -0.30
     de
    -0.30
     warm
    -0.29
     former
    -0.28
     L
    -0.28
     planning
    -0.27
    '
    -0.27
     Sha
    -0.27
     Lim
    -0.27
    POSITIVE LOGITS
    Gambas
    0.81
     Öffentlichkeit
    0.70
    对外
    0.67
     pública
    0.66
     veřej
    0.65
     terbuka
    0.65
     publique
    0.65
    TestingModule
    0.63
     ſal
    0.63
     publico
    0.62
    Activations Density 0.370%

    No Known Activations