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. 14318
    Prev
    Next
    INDEX
    Explanations

    references to the planning and organization of events or projects

    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
     tomorrow
    -0.45
     linkovi
    -0.44
    rungsseite
    -0.43
     виправивши
    -0.43
     prochaines
    -0.41
     Kontroll
    -0.39
    ciptakan
    -0.38
     Lingkungan
    -0.38
    NameInMap
    -0.38
     demain
    -0.38
    POSITIVE LOGITS
    TypedDataSet
    0.56
    styleable
    0.44
     trailed
    0.44
    extAlignment
    0.40
     drew
    0.40
    󠁬
    0.39
    inverno
    0.39
     Exactos
    0.39
     campaigned
    0.38
    ArgumentParser
    0.36
    Activations Density 0.471%

    No Known Activations