© 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. 41-GEMMASCOPE-RES-16K
    11. 4818
    Prev
    Next
    INDEX
    Explanations

    software and application development terms and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HomeAsUpEnabled
    -0.41
    intermediate
    -0.40
    Undergraduate
    -0.38
    independent
    -0.37
    Participating
    -0.37
     OFFICIAL
    -0.36
    International
    -0.36
    educational
    -0.36
    immediately
    -0.36
    CHILDREN
    -0.36
    POSITIVE LOGITS
    duino
    0.54
    plotlib
    0.54
    Droid
    0.53
     CLI
    0.52
     SDK
    0.52
     Explorer
    0.52
     Browser
    0.50
    izr
    0.50
    mapper
    0.50
    CMS
    0.50
    Activations Density 1.395%

    No Known Activations