© 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. 0-GEMMASCOPE-RES-16K
    11. 3903
    Prev
    Next
    INDEX
    Explanations

    discussions or claims involving arguments and legal assertions

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    новниш
    -0.69
     abbildung
    -0.68
    RegressionTest
    -0.66
     poffible
    -0.61
     vectorielles
    -0.60
     fhort
    -0.59
    InputBorder
    -0.59
     ſta
    -0.59
     barbati
    -0.59
     fubject
    -0.58
    POSITIVE LOGITS
     argues
    0.55
     Bay
    0.54
     undeniably
    0.48
     Belie
    0.48
     Crafted
    0.47
     arguably
    0.47
     argued
    0.47
    Bay
    0.47
     contends
    0.46
     Argu
    0.45
    Activations Density 0.252%

    No Known Activations