© 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. 15-GEMMASCOPE-RES-16K
    11. 4395
    Prev
    Next
    INDEX
    Explanations

    symbols and formatting elements used in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteTagHelper
    -0.64
    AddTagHelper
    -0.61
    =’
    -0.59
    setVerticalGroup
    -0.59
    NOPQRST
    -0.58
    sizeCache
    -0.58
    UnusedPrivate
    -0.56
    \{\\
    -0.56
     nahilalakip
    -0.55
     متعلقه
    -0.54
    POSITIVE LOGITS
    <eos>
    0.58
    참고
    0.57
    Leírás
    0.55
    PLEASE
    0.52
    "--
    0.50
    ''
    0.50
    enziali
    0.49
    --
    0.48
    pides
    0.47
    ритори
    0.46
    Activations Density 0.375%

    No Known Activations