© 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. 25-GEMMASCOPE-RES-16K
    11. 2086
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating possibility or capability

    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
    참고
    -0.57
    Chham
    -0.56
    aporan
    -0.53
     from
    -0.53
     throughout
    -0.51
    تفصیلات
    -0.50
    herself
    -0.50
     sendiri
    -0.49
     jinak
    -0.49
    usermodel
    -0.48
    POSITIVE LOGITS
     anyone
    1.39
     they
    1.38
     we
    1.36
     anybody
    1.28
     you
    1.10
     it
    0.99
    anyone
    0.98
     ANYONE
    0.95
     she
    0.92
     someone
    0.92
    Activations Density 0.146%

    No Known Activations