© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 31633
    Prev
    Next
    INDEX
    Explanations

    phrases that express critiques and evaluations of experiences or products

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

    . Would But election

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ligente
    -0.54
     Lebens
    -0.53
    Lebens
    -0.47
     assuré
    -0.44
    TagHelpers
    -0.43
     assurer
    -0.43
    megen
    -0.43
    simus
    -0.42
    DIPSETTING
    -0.42
     sinds
    -0.42
    POSITIVE LOGITS
     تضيفلها
    0.91
    LookAnd
    0.89
     HasFactory
    0.76
    )');
    0.71
    MemoryWarning
    0.71
    "]));
    0.67
    "]);
    0.67
     useAppContext
    0.67
     елның
    0.66
    ']));
    0.65
    Activations Density 0.031%

    No Known Activations