© 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 EvalsExportsinterp-engineNEWAPI 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. 4241
    Prev
    Next
    INDEX
    Explanations

    phrases related to performance metrics and comparisons

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

    "in" followed by an adjective/adverb

    np_acts-logits-general · gemini-2.0-flash

    in a way

    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
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.69
     "..\..\
    -0.68
    WebElementEntity
    -0.67
     Roskov
    -0.66
     Италијани
    -0.62
    ElementException
    -0.60
    PYX
    -0.60
     "..\..\..\
    -0.59
     astore
    -0.59
    TypedDataSet
    -0.59
    POSITIVE LOGITS
     ways
    0.77
     way
    0.67
     gré
    0.59
     maniera
    0.55
     quite
    0.53
    processable
    0.52
     Ways
    0.52
    unch
    0.52
     manières
    0.51
     subtle
    0.51
    Activations Density 0.359%

    No Known Activations