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-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 109654
    Prev
    Next
    INDEX
    Explanations

    instances of the preposition "to" and its variants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    iempos
    -0.33
    ert
    -0.32
     socials
    -0.31
     vostra
    -0.31
     lemp
    -0.31
    ベ
    -0.30
     WASH
    -0.30
     déliv
    -0.30
     Nassau
    -0.30
     washing
    -0.29
    POSITIVE LOGITS
    setVerticalGroup
    0.71
    hoeddwyd
    0.71
     Houſe
    0.63
    richTextPanel
    0.63
     purpoſe
    0.61
     houſe
    0.59
    ſelf
    0.57
    PreInfinity
    0.56
     ویکی‌پدی
    0.55
    tagHelperRunner
    0.55
    Activations Density 0.001%

    No Known Activations