© 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. 8433
    Prev
    Next
    INDEX
    Explanations

    instances of the prefix "ins," particularly in a context that suggests negativity or wrongdoing

    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
     ExecuteAsync
    -0.76
    pausal
    -0.57
     eenige
    -0.54
     hardness
    -0.54
    yně
    -0.52
     moeite
    -0.52
    elry
    -0.51
    arised
    -0.51
    attribs
    -0.50
    كات
    -0.50
    POSITIVE LOGITS
    ⓧ
    0.66
    jaro
    0.52
    يكب
    0.51
    ="@+
    0.49
    encodeWith
    0.49
    webElementXpaths
    0.49
    IsContent
    0.48
    esgue
    0.48
     astore
    0.47
     ModelAndView
    0.47
    Activations Density 0.219%

    No Known Activations