© 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. 8582
    Prev
    Next
    INDEX
    Explanations

    sentences that end with punctuation marks, particularly periods or quotes

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

    Code, error messages, or names

    np_acts-logits-general · gemini-2.0-flash

    legal jargon and formatting

    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
    nonatomic
    -0.57
     HttpNotFound
    -0.53
     _('
    -0.49
    SourceChecksum
    -0.47
     considérons
    -0.47
    kään
    -0.47
    inSlope
    -0.47
    Recommend
    -0.47
    はじめに
    -0.46
    NavController
    -0.46
    POSITIVE LOGITS
    format
    0.68
    findpost
    0.64
    "".
    0.59
    ContentAlignment
    0.59
     متعلقه
    0.55
     DRY
    0.55
    তথ্যসূত্র
    0.54
    Notae
    0.53
    maphore
    0.52
    formin
    0.52
    Activations Density 0.082%

    No Known Activations