© 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
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 11875
    Prev
    Next
    INDEX
    Explanations

    technical language related to computer systems and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.69
     AssemblyCulture
    -0.42
    ypeł
    -0.40
     rajut
    -0.37
     incluem
    -0.36
     tewas
    -0.36
     CURIAM
    -0.36
     vodi
    -0.35
     ainfi
    -0.35
     nauczy
    -0.35
    POSITIVE LOGITS
    ChildScrollView
    0.74
    ValueStyle
    0.67
    nodoc
    0.59
    contentValues
    0.57
    currentColor
    0.57
    fastjson
    0.57
    kmale
    0.56
     defaultstate
    0.56
    ngdoc
    0.54
    obar
    0.53
    Activations Density 1.118%

    No Known Activations