© 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. 16-GEMMASCOPE-RES-16K
    11. 10545
    Prev
    Next
    INDEX
    Explanations

    phrases concerning the significance of individual expression and personality in various contexts

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

    after certain common words

    np_acts-logits-general · gemini-2.0-flash

    what actually happens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ArgsConstructor
    -0.87
    istoitu
    -0.80
    MemoryWarning
    -0.79
     DOWNVOTE
    -0.78
     IndexPath
    -0.74
    XmlAccessType
    -0.73
    RTLD
    -0.71
     Normdatei
    -0.70
    Personensuche
    -0.70
     NDEBUG
    -0.70
    POSITIVE LOGITS
    <em>
    0.61
     selve
    0.59
    却是
    0.56
     actually
    0.56
    <i>
    0.55
    それだけ
    0.55
     other
    0.53
    なんですよ
    0.50
    整個
    0.49
     also
    0.49
    Activations Density 0.543%

    No Known Activations