© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. MLP Out - 16k
    5. 19-GEMMASCOPE-MLP-16K
    6. 9186
    Prev
    Next
    INDEX
    Explanations

    phrases related to social interactions or expressions of emotions

    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
     &
    -0.57
     
    -0.56
    -
    -0.50
     Super
    -0.47
     in
    -0.46
    anus
    -0.45
    ,
    -0.45
     (
    -0.44
    </blockquote>
    -0.44
    ish
    -0.44
    POSITIVE LOGITS
    tvguidetime
    1.05
    \{\\
    1.03
     Савезне
    1.02
     Majefty
    0.97
     ་་
    0.96
     Efq
    0.93
     iſt
    0.93
     ſind
    0.92
     myſelf
    0.92
     ―――――
    0.91
    Activations Density 0.100%

    No Known Activations