© 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. 12623
    Prev
    Next
    INDEX
    Explanations

    patterns of code structure, particularly focusing on closing brackets and syntactical delimiters

    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
    DeleteBehavior
    -0.56
    ConstraintMaker
    -0.49
    Diwedd
    -0.48
     continúas
    -0.47
    杓
    -0.40
     мәкал
    -0.40
    !*\
    -0.39
     }}"></
    -0.39
     straightening
    -0.39
    ̈́
    -0.39
    POSITIVE LOGITS
     else
    0.85
    else
    0.64
     Else
    0.62
     Otherwise
    0.62
    否则
    0.60
     otherwise
    0.59
    Otherwise
    0.58
    Else
    0.58
    elif
    0.56
    fjspx
    0.56
    Activations Density 0.140%

    No Known Activations