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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 108382
    Prev
    Next
    INDEX
    Explanations

    references to specific positions or indices in a data 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
     position
    -1.36
    position
    -1.36
     Position
    -1.26
     POSITION
    -1.09
     Positions
    -1.08
     positions
    -1.06
    Position
    -1.05
     posizione
    -1.04
     posición
    -0.98
    POSITION
    -0.96
    POSITIVE LOGITS
    雏
    0.37
    Induced
    0.33
    talk
    0.31
    Closure
    0.31
    équ
    0.31
    induced
    0.30
     imperfect
    0.30
     loose
    0.30
     ropes
    0.30
     grader
    0.30
    Activations Density 0.001%

    No Known Activations