© 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. 18-GEMMASCOPE-RES-16K
    11. 9799
    Prev
    Next
    INDEX
    Explanations

    phrases related to social media interactions and recognition

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

    Text preceding words like "with", "and", "for", or "on"

    np_acts-logits-general · gemini-2.0-flash

    news headlines and media topics

    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
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.87
     فريبيس
    -0.86
     ModelExpression
    -0.84
    expandindo
    -0.81
     Савезне
    -0.79
    :✨
    -0.79
    GEBURTSDATUM
    -0.78
    ConstraintMaker
    -0.76
     saites
    -0.76
    NamedQueries
    -0.75
    POSITIVE LOGITS
     [
    0.80
     |
    0.71
    youtu
    0.58
    │
    0.54
    |
    0.53
    ⋆
    0.51
    <eos>
    0.49
     -
    0.49
    [
    0.47
    VIDEO
    0.47
    Activations Density 0.163%

    No Known Activations