© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 13298
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their patterns in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     importantly
    -0.66
     overall
    -0.56
     deuil
    -0.56
    yep
    -0.54
     Importantly
    -0.54
     forgiven
    -0.53
     additionally
    -0.53
    ConfigureAwait
    -0.53
    overall
    -0.53
    ioutil
    -0.52
    POSITIVE LOGITS
     Tho
    0.66
     كومونز
    0.61
     Wherefore
    0.60
     There
    0.57
     It
    0.57
     Such
    0.56
    elter
    0.56
     The
    0.56
     But
    0.54
     Possibly
    0.54
    Activations Density 0.398%

    No Known Activations