© 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. 12-GEMMASCOPE-RES-16K
    11. 7851
    Prev
    Next
    INDEX
    Explanations

    terms related to significant findings or claims in various studies or reports

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     équilibr
    -0.50
     przecież
    -0.49
    technologies
    -0.45
     TECHNOLOGIES
    -0.44
     pinulongan
    -0.43
     takže
    -0.42
     girlfriends
    -0.42
    ագրություններ
    -0.42
    Ведь
    -0.42
    appareil
    -0.42
    POSITIVE LOGITS
     Administrativna
    0.62
    LabelTagHelper
    0.59
    coltà
    0.44
     XCTest
    0.44
     convertView
    0.43
    olulu
    0.42
     direct
    0.42
     relu
    0.42
     propOrder
    0.41
     belief
    0.41
    Activations Density 1.173%

    No Known Activations