© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 27702
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence of information or content

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    identifying what is contained

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     newUser
    -0.73
     $_(
    -0.73
     $_"
    -0.71
    "$_
    -0.68
    parsedMessage
    -0.67
     étoient
    -0.63
    GenerationType
    -0.61
     ſch
    -0.60
     avoient
    -0.60
     Gesture
    -0.60
    POSITIVE LOGITS
     contains
    1.63
     contain
    1.53
     Contains
    1.38
    contains
    1.35
    Contains
    1.34
    contain
    1.30
     containing
    1.28
     Contain
    1.25
    Contain
    1.21
     contained
    1.12
    Activations Density 0.022%

    No Known Activations