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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 109545
    Prev
    Next
    INDEX
    Explanations

    activities related to competitive racing

    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
     raced
    -0.79
    ConstraintMaker
    -0.63
     racing
    -0.63
     race
    -0.55
    IntoConstraints
    -0.54
     للاسماء
    -0.54
     racer
    -0.50
    racing
    -0.50
     races
    -0.47
     racers
    -0.46
    POSITIVE LOGITS
     Ponto
    0.40
    AndroidJUnit
    0.40
    Vidite
    0.39
     becauſe
    0.39
    reactstrap
    0.38
    nloa
    0.38
    schirm
    0.38
    specifier
    0.36
     Ober
    0.36
    Ober
    0.36
    Activations Density 0.003%

    No Known Activations