© 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. 10329
    Prev
    Next
    INDEX
    Explanations

    expressions related to object definitions and method implementations

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

    "Bar" or comes after specific words

    np_acts-logits-general · gemini-2.0-flash

    .bar

    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
    GraphicsUnit
    -0.78
     esboço
    -0.61
     cherchés
    -0.58
    DispatchToProps
    -0.58
     AssemblyCompany
    -0.57
    렷
    -0.55
    urnum
    -0.55
    abestanden
    -0.53
     AssemblyCulture
    -0.53
    qtype
    -0.53
    POSITIVE LOGITS
     bar
    3.93
     Bar
    3.75
    Bar
    3.65
    bar
    3.63
    BAR
    3.19
     BAR
    3.16
     bars
    2.81
     Bars
    2.55
    bars
    2.55
    Bars
    2.33
    Activations Density 0.454%

    No Known Activations