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. 16-GEMMASCOPE-RES-16K
    6. 12238
    Prev
    Next
    INDEX
    Explanations

    the beginning of a new section or concept in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows specific words: "Related", "\", "of"

    np_acts-logits-general · gemini-2.0-flash

    lists of words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elemField
    -0.72
     CreateTagHelper
    -0.67
     AssemblyCulture
    -0.66
    WithIOException
    -0.61
     متحده
    -0.60
    GZIP
    -0.58
    igshid
    -0.56
    CloseOperation
    -0.55
    EObject
    -0.54
    UnknownFieldSet
    -0.54
    POSITIVE LOGITS
     OnTrigger
    0.50
    حياتها
    0.49
    esgue
    0.49
    الحياه
    0.46
     Aris
    0.46
     finalised
    0.44
     licenci
    0.43
     privatisation
    0.42
     лёг
    0.42
     трёх
    0.42
    Activations Density 0.014%

    No Known Activations