Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. MLP Out - 16k
    5. 22-GEMMASCOPE-MLP-16K
    6. 15788
    Prev
    Next
    INDEX
    Explanations

    technical and mathematical expressions related to fluid dynamics and stress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_mlp_out
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    scriptcase
    -0.67
    InitVars
    -0.67
     defaultstate
    -0.66
    endregion
    -0.59
    oneofs
    -0.59
     PyObject
    -0.57
    AndEndTag
    -0.57
    CppMethod
    -0.56
     Wayback
    -0.56
     HttpContext
    -0.55
    POSITIVE LOGITS
    eseorang
    0.55
     Füße
    0.52
     gluon
    0.49
    zdo
    0.49
    MENAFN
    0.48
    eleste
    0.48
     Partagez
    0.47
     predators
    0.47
     raiſ
    0.47
    ediakan
    0.47
    Activations Density 0.886%

    No Known Activations