© 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. 15775
    Prev
    Next
    INDEX
    Explanations

    key information related to mobile application development

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

    Follows a short word or abbreviation

    np_acts-logits-general · gemini-2.0-flash

    finding product price and availability

    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
    TintMode
    -0.72
    windowFixed
    -0.70
    FormTagHelper
    -0.63
    openzeppelin
    -0.63
     '\\;'
    -0.62
    PreferredItem
    -0.61
    antası
    -0.61
     AssemblyCulture
    -0.60
    bcryptjs
    -0.59
    parsedMessage
    -0.58
    POSITIVE LOGITS
    timewa
    0.58
    ampe
    0.55
     damit
    0.52
    CHER
    0.49
     Klä
    0.48
    truk
    0.48
    -(
    0.48
    cupertino
    0.47
     Hush
    0.47
     Hock
    0.46
    Activations Density 0.045%

    No Known Activations