© 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. 18-GEMMASCOPE-RES-16K
    11. 3259
    Prev
    Next
    INDEX
    Explanations

    phrases related to customer needs and product solutions

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

    Follows a form of "is" or "are"

    np_acts-logits-general · gemini-2.0-flash

    forms of "to be"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    contentLoaded
    -0.72
     protoimpl
    -0.68
    )"),
    -0.66
    Referencies
    -0.65
    Nationalité
    -0.64
     isInitialized
    -0.61
     Keil
    -0.61
    VideoCapture
    -0.61
    ViewFeatures
    -0.61
    Склад
    -0.60
    POSITIVE LOGITS
     nichts
    0.48
    twimg
    0.48
    <0xEA>
    0.45
     followed
    0.45
     worth
    0.44
    alles
    0.43
     jegy
    0.43
     about
    0.42
     sitä
    0.42
     woda
    0.42
    Activations Density 0.046%

    No Known Activations