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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7568
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to definitions or explanations within a theoretical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    iNdEx
    -0.66
    AccessorTable
    -0.66
    Obrázky
    -0.60
    bootstrapcdn
    -0.59
    styleType
    -0.54
     voici
    -0.52
    HomeAsUp
    -0.50
    ArrowToggle
    -0.50
    पया
    -0.49
     AppCompatTheme
    -0.49
    POSITIVE LOGITS
     terms
    3.09
    terms
    2.50
     Terms
    2.26
    Terms
    2.23
     TERMS
    2.20
     termes
    2.11
     términos
    2.00
    TERMS
    1.91
     termos
    1.80
     term
    1.71
    Activations Density 0.395%

    No Known Activations