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. 2219
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical conditions and their effects, particularly conjunctivitis and its symptoms

    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
    PerformLayout
    -0.46
    новништво
    -0.43
    RenderAtEndOf
    -0.36
    ophora
    -0.32
    FormTagHelper
    -0.32
    PARSER
    -0.31
     kering
    -0.30
     miners
    -0.30
     Yor
    -0.29
     stands
    -0.28
    POSITIVE LOGITS
     greateſt
    0.54
     nahilalakip
    0.53
    principalColumn
    0.51
     uſed
    0.51
    WebVitals
    0.50
     disambiguazione
    0.50
     ſtre
    0.50
     abſ
    0.49
     fevere
    0.49
    homonymie
    0.49
    Activations Density 0.801%

    No Known Activations