© 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. MLP Out - 16k
    9. 19-GEMMASCOPE-MLP-16K
    11. 7021
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the taking of something for granted

    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
     bracket
    -0.47
    oose
    -0.47
     M
    -0.45
     مواليد
    -0.44
    pota
    -0.44
    Navigator
    -0.44
    UNA
    -0.43
    GoogleApiClient
    -0.42
     Adam
    -0.42
    ada
    -0.42
    POSITIVE LOGITS
     الحره
    0.85
    AddTagHelper
    0.78
    mybatisplus
    0.77
    ftagPool
    0.76
     виправивши
    0.75
     granted
    0.72
    featureID
    0.70
     NUKAT
    0.69
    AsUp
    0.69
    ValueStyle
    0.67
    Activations Density 0.339%

    No Known Activations