© 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. 110015
    Prev
    Next
    INDEX
    Explanations

    terms related to structures, processes, or systems, particularly in technical or operational 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
     kaarangay
    -0.72
     препратки
    -0.71
     sumpay
    -0.66
    rungsseite
    -0.65
     HasFactory
    -0.62
    routeProvider
    -0.60
     desmotivaciones
    -0.59
    клопе
    -0.59
    Autoritní
    -0.58
    хьтан
    -0.58
    POSITIVE LOGITS
    Shaders
    0.35
    Exist
    0.32
     Tro
    0.32
     Tab
    0.31
    Cred
    0.31
    Tab
    0.31
     lago
    0.30
     fea
    0.30
    por
    0.29
     Sal
    0.29
    Activations Density 0.032%

    No Known Activations