© 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. 36-GEMMASCOPE-RES-16K
    11. 9693
    Prev
    Next
    INDEX
    Explanations

    elements related to software updates or bug tracking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageOf
    -0.70
     useAppContext
    -0.66
     linkovi
    -0.59
     Roskov
    -0.57
    AddTagHelper
    -0.54
    RenderAtEndOf
    -0.54
    MessageTagHelper
    -0.54
    CppMethod
    -0.54
    SequentialGroup
    -0.54
    makeText
    -0.53
    POSITIVE LOGITS
     bug
    1.15
     issue
    1.02
     Bug
    1.00
     Issue
    0.96
    Issue
    0.89
    issue
    0.87
    Bug
    0.85
     bugs
    0.84
    bug
    0.83
     PR
    0.79
    Activations Density 1.145%

    No Known Activations