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. 15827
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and web development

    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
     Audiodateien
    -0.73
    <?
    -0.67
    ResumeLayout
    -0.64
     Мексичка
    -0.60
     jspb
    -0.57
    ngdoc
    -0.57
    toHaveBeenCalled
    -0.54
     chi̍t
    -0.54
    Hrsg
    -0.53
     intptr
    -0.51
    POSITIVE LOGITS
    /
    2.13
    /$
    1.45
    /"
    1.44
    /${
    1.41
    /{
    1.38
    /
    1.38
    /%
    1.35
    /_
    1.34
    /'
    1.33
    /(
    1.32
    Activations Density 1.303%

    No Known Activations