© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 12913
    Prev
    Next
    INDEX
    Explanations

    HTML elements and their attributes related to scripts and string data within the document

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

    HTML script or string tags

    np_acts-logits-general · gemini-2.0-flash

    script tags with type or src and string tags with name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.70
     élas
    -0.66
    PyTuple
    -0.59
    Enllaces
    -0.58
     sociali
    -0.56
    InitVars
    -0.54
     <=",
    -0.54
     commerciales
    -0.53
    انتهای
    -0.51
     définiti
    -0.51
    POSITIVE LOGITS
    translation
    0.80
     type
    0.73
    heureusement
    0.57
    numerusform
    0.50
    furn
    0.50
    paru
    0.50
     Fili
    0.50
     Bir
    0.50
     doPost
    0.49
     [*]
    0.49
    Activations Density 0.032%

    No Known Activations