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. 109701
    Prev
    Next
    INDEX
    Explanations

    programming and grammatical constructs related to syntax and structure

    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
    featureID
    -0.44
     ביט
    -0.40
     construct
    -0.40
     constructs
    -0.40
     trekken
    -0.37
     licencia
    -0.37
    GOTREF
    -0.37
    principalColumn
    -0.35
     expediente
    -0.35
    ftagPool
    -0.35
    POSITIVE LOGITS
     betweenstory
    0.55
    setVerticalGroup
    0.52
     GenerationType
    0.51
    UNRELATED
    0.51
    MemoryWarning
    0.47
     Wachs
    0.46
    τερα
    0.45
     <>",
    0.45
    clonal
    0.44
    atoare
    0.43
    Activations Density 0.204%

    No Known Activations