© 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. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 302
    Prev
    Next
    INDEX
    Explanations

    instances of specific terms or identifiers related to data processing or technical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jednot
    -0.37
     obě
    -0.33
     nød
    -0.32
     Kimball
    -0.31
     endnu
    -0.31
     nogen
    -0.31
    numerusform
    -0.31
     Breen
    -0.31
     Rabin
    -0.31
     samman
    -0.31
    POSITIVE LOGITS
     SL
    2.30
     sl
    2.20
     Sl
    2.19
     Sla
    2.16
     sla
    2.08
    SL
    2.06
    Sl
    2.03
    Sla
    2.03
    sl
    1.98
     Sli
    1.94
    Activations Density 1.500%

    No Known Activations