© 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. 35-GEMMASCOPE-RES-16K
    11. 10424
    Prev
    Next
    INDEX
    Explanations

    terms related to specific brands and technical specifications

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     ModelRenderer
    -0.41
    Can
    -0.38
    col
    -0.38
    Col
    -0.38
    COL
    -0.38
    PER
    -0.37
     Can
    -0.36
     Col
    -0.35
     poveznice
    -0.35
    AxisAlignment
    -0.34
    POSITIVE LOGITS
    Hentet
    0.58
    tagHelperRunner
    0.53
    GOTREF
    0.53
    StoryboardSegue
    0.53
    Lycka
    0.52
     surla
    0.52
     chinoise
    0.52
    enderror
    0.51
     Administrativna
    0.50
     useAppContext
    0.49
    Activations Density 1.421%

    No Known Activations