© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 15563
    Prev
    Next
    INDEX
    Explanations

    terms related to 3D vector concepts and properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    protoimpl
    -0.78
     nakalista
    -0.75
     bezeichneter
    -0.74
    Mule
    -0.74
     Pilate
    -0.68
    FunctionFlags
    -0.65
     Cæsar
    -0.65
     Slovenian
    -0.63
     okuyayım
    -0.62
     Mule
    -0.61
    POSITIVE LOGITS
    Vector
    1.54
     Vector
    1.50
    minecraft
    0.61
    Portály
    0.57
     VECTOR
    0.56
     chi̍t
    0.55
    السكان
    0.53
    VECTOR
    0.52
    textSize
    0.51
    kloped
    0.49
    Activations Density 0.139%

    No Known Activations