© 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. 40-GEMMASCOPE-RES-16K
    11. 7189
    Prev
    Next
    INDEX
    Explanations

    formatted references and citations typically seen in academic papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.67
    
    -0.66
     μὲν
    -0.62
    AddTagHelper
    -0.60
     BoxFit
    -0.59
    InitVars
    -0.57
    ########.
    -0.56
     CURIAM
    -0.56
     <<<<<<<<<<<<<<
    -0.54
    出版年
    -0.53
    POSITIVE LOGITS
     pp
    0.80
    pp
    0.44
     PP
    0.43
     р
    0.42
     ),
    0.29
     p
    0.28
    pps
    0.28
     Système
    0.28
     po
    0.28
     ​​
    0.27
    Activations Density 0.453%

    No Known Activations