© 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. 20-GEMMASCOPE-RES-131K
    11. 66558
    Prev
    Next
    INDEX
    Explanations

    coordinate vectors associated with shadow calculations in graphical programming

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

    vec3 or math notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ỏa
    -0.46
    brill
    -0.45
    //
    -0.45
     
    -0.44
     Osborne
    -0.44
    PTION
    -0.44
     Harding
    -0.44
     للاسماء
    -0.43
    tony
    -0.43
     I
    -0.42
    POSITIVE LOGITS
    Vec
    1.11
    vec
    1.08
     vec
    1.06
     Vec
    1.05
    VEC
    0.81
     vectorielles
    0.76
    ovec
    0.70
     vectorielle
    0.69
    vektor
    0.68
     vecteur
    0.67
    Activations Density 0.003%

    No Known Activations