© 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. 15047
    Prev
    Next
    INDEX
    Explanations

    names and terms related to specific products or software entities

    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
    ed
    -0.57
    ponte
    -0.52
     Either
    -0.51
     Dä
    -0.50
    hashtags
    -0.49
    GRANTED
    -0.49
    EnableWeb
    -0.48
     CommonModule
    -0.47
    Either
    -0.46
     Other
    -0.45
    POSITIVE LOGITS
    DoubleQuotes
    0.71
    ніципалі
    0.59
    KommentareTeilen
    0.58
     Hima
    0.57
    rhosis
    0.56
     kasarigan
    0.56
     biografias
    0.54
    DataBinding
    0.53
    GINIA
    0.53
    inya
    0.52
    Activations Density 0.187%

    No Known Activations