© 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. MLP Out - 16k
    9. 19-GEMMASCOPE-MLP-16K
    11. 9005
    Prev
    Next
    INDEX
    Explanations

    positive words and phrases indicating appreciation or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_19/width_16k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_mlp_out
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     advantage
    -1.52
    advantage
    -1.31
    Advantage
    -1.19
     benefit
    -1.18
     Advantage
    -1.09
     advantageous
    -1.08
     advantages
    -1.07
    avantage
    -1.05
     Vorteil
    -1.05
    benefit
    -1.02
    POSITIVE LOGITS
    enfone
    0.52
    Pfalz
    0.50
    uesia
    0.47
    KommentareTeilen
    0.47
     florales
    0.47
     farba
    0.46
    ècie
    0.46
    ableView
    0.45
    strSql
    0.44
     RestTemplate
    0.43
    Activations Density 0.582%

    No Known Activations