© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 61383
    Prev
    Next
    INDEX
    Explanations

    references to stereo or stereoscopic imaging and audio systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    stereo pair

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    octanol
    -0.48
     Covid
    -0.48
    Poppins
    -0.48
     Valorant
    -0.47
     Nox
    -0.47
    Doch
    -0.47
     COVID
    -0.47
     OkHttpClient
    -0.46
    勾
    -0.46
     المعيارى
    -0.45
    POSITIVE LOGITS
     stereo
    1.89
     Stereo
    1.80
    Stereo
    1.77
    stereo
    1.72
     stere
    1.45
    EREO
    1.36
    Stere
    1.23
    stere
    1.23
     Stere
    1.22
    éreo
    0.88
    Activations Density 0.010%

    No Known Activations