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. 7034
    Prev
    Next
    INDEX
    Explanations

    specific settings and locations related to health and community studies

    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
    Geplaatst
    -0.49
    ScopeManager
    -0.48
    protoimpl
    -0.44
    IVEREF
    -0.44
    tvguidetime
    -0.43
     Савезне
    -0.43
    WriteTagHelper
    -0.41
     Eſ
    -0.41
    AsUp
    -0.41
    MLLoader
    -0.40
    POSITIVE LOGITS
     locations
    0.96
     Locations
    0.82
     location
    0.80
    locations
    0.78
    Locations
    0.76
     locatie
    0.71
     LOCATIONS
    0.71
    location
    0.69
     locales
    0.68
     località
    0.64
    Activations Density 1.041%

    No Known Activations