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. 20-GEMMASCOPE-RES-16K
    6. 9440
    Prev
    Next
    INDEX
    Explanations

    statements and quotations from various sources

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

    Comes before a quotation

    np_acts-logits-general · gemini-2.0-flash

    reported speech verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.71
    iecie
    -0.69
    utilisons
    -0.67
     Monfieur
    -0.62
     Majefty
    -0.60
    AccessFile
    -0.57
     Houſe
    -0.57
    cámara
    -0.56
     Anſ
    -0.55
     Mémoires
    -0.55
    POSITIVE LOGITS
    :
    0.85
     although
    0.80
     “
    0.77
    :“
    0.77
     pihaknya
    0.75
    :“
    0.73
    :”
    0.70
     the
    0.69
    SourceChecksum
    0.68
     there
    0.67
    Activations Density 0.213%

    No Known Activations