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. 6-GEMMASCOPE-MLP-16K
    6. 20
    Prev
    Next
    INDEX
    Explanations

    expressions of opinion or judgment related to arguments or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.59
     ordina
    -0.57
     hierogly
    -0.54
    UnsafeEnabled
    -0.53
     regeneration
    -0.51
    جع
    -0.51
    )";
    
    -0.51
     Klagen
    -0.50
    .",
    
    -0.50
     Maar
    -0.50
    POSITIVE LOGITS
    tonode
    0.84
     الرياضيه
    0.61
    phère
    0.56
     &___
    0.56
     lagi
    0.56
    Gweler
    0.55
     <=",
    0.54
    roidery
    0.54
     Italijani
    0.53
    fortawesome
    0.53
    Activations Density 0.309%

    No Known Activations