© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 5273
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks, specifically apostrophes and quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.83
     the
    -0.67
    <bos>
    -0.64
    ’
    -0.60
     a
    -0.59
    '
    -0.54
    blems
    -0.54
     co
    -0.52
    [toxicity=0]
    -0.51
     of
    -0.51
    POSITIVE LOGITS
    GEBURTSDATUM
    1.37
     propOrder
    1.10
    -'
    1.09
     (‘
    1.06
    MigrationBuilder
    1.01
    :'
    1.01
     ‚
    0.99
    EDEFAULT
    0.98
    verwijspagina
    0.96
    ?'
    0.95
    Activations Density 0.158%

    No Known Activations