© 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. 109915
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce or modify a clause, particularly relative pronouns and conjunctions

    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
    ⓧ
    -0.73
    AndEndTag
    -0.64
     disambiguazione
    -0.60
     ivelany
    -0.59
     ComVisible
    -0.56
    MessageOf
    -0.56
    LookAnd
    -0.53
    Tikang
    -0.50
     noDo
    -0.50
     StatelessWidget
    -0.49
    POSITIVE LOGITS
    .*")]
    0.45
     scope
    0.36
    =((
    0.34
     referrerpolicy
    0.34
     kapak
    0.34
     space
    0.32
    (((
    0.32
     room
    0.31
     (((
    0.30
    ValueType
    0.29
    Activations Density 0.016%

    No Known Activations