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. 538
    Prev
    Next
    INDEX
    Explanations

    references to regions or locations described in a technical context

    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
    %)$
    -0.33
    cepteur
    -0.32
    LEncoder
    -0.31
    KURZBESCHREIBUNG
    -0.30
     nonUne
    -0.30
     wikipagina
    -0.30
     cook
    -0.30
     associated
    -0.29
    Počet
    -0.29
    化的
    -0.29
    POSITIVE LOGITS
    EndContext
    0.69
     next
    0.62
     nästa
    0.57
    下一个
    0.56
    webElementXpaths
    0.56
     NEXT
    0.56
     предыду
    0.55
    previous
    0.53
    next
    0.53
    Demografie
    0.51
    Activations Density 0.865%

    No Known Activations