© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 23-GEMMASCOPE-RES-16K
    11. 8330
    Prev
    Next
    INDEX
    Explanations

    variations of the word "bl" and its associated usages

    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
    makeConstraints
    -0.61
    JNIEnv
    -0.60
    WriteBarrier
    -0.60
    Personensuche
    -0.56
     tegens
    -0.55
    webElementXpaths
    -0.54
     нав
    -0.52
     /\.(
    -0.50
     trampoline
    -0.49
     liberi
    -0.49
    POSITIVE LOGITS
     Bla
    0.61
    )|^{
    0.60
     Bl
    0.60
     bla
    0.59
    zzard
    0.56
    Bla
    0.56
    bla
    0.56
    MLLoader
    0.56
    IBLIO
    0.55
     bl
    0.54
    Activations Density 0.146%

    No Known Activations