© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 110083
    Prev
    Next
    INDEX
    Explanations

    terms related to prior knowledge or assumptions in a mathematical context

    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
     priori
    -1.62
     posteriori
    -0.62
     PRIOR
    -0.54
     priors
    -0.52
    prior
    -0.51
     prior
    -0.50
     Prior
    -0.49
    Prior
    -0.46
     apri
    -0.46
    
    -0.43
    POSITIVE LOGITS
    يميديا
    0.51
    يكب
    0.44
    Trama
    0.43
    Twice
    0.42
     FINE
    0.42
    SdkVersion
    0.42
     thinner
    0.40
     bonding
    0.40
    psack
    0.40
     sorting
    0.40
    Activations Density 0.003%

    No Known Activations