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

    Neuronpedia

    Jacobian LensNEW
    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. 24-GEMMASCOPE-RES-16K
    11. 10082
    Prev
    Next
    INDEX
    Explanations

    concepts related to business practices and product quality

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

    describing an attribute or characteristic

    np_acts-logits-general · gemini-2.0-flash

    descriptive content or subject matter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WAUKEE
    -0.59
    timewa
    -0.57
    vestres
    -0.52
    RUnlock
    -0.52
    urably
    -0.51
     TAMBIÉN
    -0.51
    ưỡi
    -0.50
     behalf
    -0.50
    기도
    -0.49
    دیگر
    -0.49
    POSITIVE LOGITS
     backed
    1.03
     with
    1.01
     requiring
    1.01
     punctuated
    1.00
     devoid
    0.98
     surrounded
    0.98
     designed
    0.93
     accompanied
    0.93
     characterized
    0.92
     powered
    0.90
    Activations Density 0.734%

    No Known Activations