© 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. 23-GEMMASCOPE-RES-16K
    6. 11537
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating requests and possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    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
    -0.70
    تفصیلات
    -0.69
     său
    -0.68
    EDEFAULT
    -0.67
    ">—
    -0.67
    참고
    -0.67
     становника
    -0.67
     Roskov
    -0.66
     Infórmanos
    -0.64
    AsUp
    -0.63
    POSITIVE LOGITS
     they
    1.73
     we
    1.50
     you
    1.39
     anyone
    1.36
     anybody
    1.21
     it
    1.17
     there
    1.03
    anyone
    1.00
     someone
    0.97
     они
    0.96
    Activations Density 0.193%

    No Known Activations