© 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. 20-GEMMASCOPE-RES-16K
    11. 16382
    Prev
    Next
    INDEX
    Explanations

    elements that convey emotional or aesthetic qualities

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

    preceding "to" or describing a feeling/quality

    np_acts-logits-general · gemini-2.0-flash

    describing abstract qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.66
    \{\\
    -0.64
    Бахар
    -0.64
    ativement
    -0.64
    contentLoaded
    -0.63
     Houſe
    -0.63
     Efq
    -0.62
    StoryboardSegue
    -0.60
    Geplaatst
    -0.59
    expandindo
    -0.59
    POSITIVE LOGITS
     about
    0.70
    attached
    0.55
    added
    0.54
     attached
    0.54
    about
    0.52
     imparted
    0.49
     added
    0.49
     element
    0.47
     vibe
    0.47
    assertj
    0.46
    Activations Density 0.164%

    No Known Activations