© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 2165
    Prev
    Next
    INDEX
    Explanations

    advertisements and promotional content within the text

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Sentences and fragments ending with a period

    np_acts-logits-general · gemini-2.0-flash

    Read More Advertisement

    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
    Negative Logits
    Demikian
    -0.58
     myself
    -0.52
     Somit
    -0.51
    Semoga
    -0.48
    pozdrawiam
    -0.48
    Pozdrawiam
    -0.48
    弊社
    -0.47
     Myself
    -0.47
    drawiam
    -0.47
     Espero
    -0.47
    POSITIVE LOGITS
    RELATED
    1.09
     RELATED
    1.09
    READ
    0.99
     READ
    0.94
     Related
    0.93
    Related
    0.92
     PHOTOS
    0.86
    MORE
    0.83
     Advertisement
    0.82
    Advertisement
    0.82
    Activations Density 0.098%

    No Known Activations