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. 126
    Prev
    Next
    INDEX
    Explanations

    actions related to legal procedures and courtroom dynamics

    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
     uſe
    -0.72
    rrbracket
    -0.66
     encode
    -0.65
     compete
    -0.65
     personalize
    -0.62
     تانيه
    -0.62
     harden
    -0.60
     retract
    -0.60
    MessageState
    -0.60
     remove
    -0.59
    POSITIVE LOGITS
    parsedMessage
    0.69
    XmlAccessorType
    0.68
    OGND
    0.64
    Rüyada
    0.64
     propOrder
    0.59
    ting
    0.59
     @"/
    0.59
    TargetApi
    0.59
     noqa
    0.59
    IsMutable
    0.59
    Activations Density 0.976%

    No Known Activations