© 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. 109097
    Prev
    Next
    INDEX
    Explanations

    references to age, particularly in relation to the concept of "old."

    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
    ніципалі
    -0.38
    MessageTagHelper
    -0.38
     Italij
    -0.36
    Dettagli
    -0.36
     mouvement
    -0.34
    service
    -0.33
     äl
    -0.33
     auffi
    -0.32
     fonds
    -0.32
     zanahoria
    -0.32
    POSITIVE LOGITS
     snippetHide
    0.70
    Personendaten
    0.65
     @"/
    0.60
    .*")]
    0.56
     Administrativna
    0.54
    dAtA
    0.53
    PYX
    0.53
    >{@
    0.51
    ArrowToggle
    0.50
     propOrder
    0.50
    Activations Density 0.002%

    No Known Activations