© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 14812
    Prev
    Next
    INDEX
    Explanations

    keywords and concepts related to Python modules and class definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tekem
    -0.49
    runt
    -0.49
    •
    -0.47
     victimes
    -0.47
     precedenti
    -0.46
     légiti
    -0.44
     dagens
    -0.44
    <sup>
    -0.43
     baterías
    -0.43
     oyn
    -0.43
    POSITIVE LOGITS
    ItemBackground
    0.88
    IUrlHelper
    0.76
    SequentialGroup
    0.76
    msgTypes
    0.66
     nahilalakip
    0.66
    servable
    0.66
     насељу
    0.66
    styleable
    0.66
    UnsafeEnabled
    0.65
     ***!
    0.64
    Activations Density 0.223%

    No Known Activations