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. 7178
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "to be" in various forms and tenses

    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
    uncurkan
    -0.43
     amizade
    -0.40
     a
    -0.38
     épa
    -0.38
    /**
    -0.37
    zbęd
    -0.36
     Grundlage
    -0.35
     durer
    -0.35
     Klicken
    -0.34
     plegable
    -0.34
    POSITIVE LOGITS
     betweenstory
    0.81
     GenerationType
    0.74
     wireType
    0.72
    ualaikum
    0.69
    
    0.68
    ViewImports
    0.66
     raiſ
    0.65
     Administrativna
    0.63
    FormTagHelper
    0.62
     myſelf
    0.62
    Activations Density 0.283%

    No Known Activations