© 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. 4-GEMMASCOPE-RES-16K
    11. 11702
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols related to matrices and vectors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -1.05
    fjspx
    -1.02
     tartalomajánló
    -0.91
    ึกษา
    -0.87
    uxxxx
    -0.85
    UnsafeEnabled
    -0.83
    FunctionFlags
    -0.81
    دانشنامهٔ
    -0.81
     bezeichneter
    -0.80
     Bred
    -0.79
    POSITIVE LOGITS
    mathbf
    2.60
    boldsymbol
    1.12
    jenigen
    0.70
    textbf
    0.69
     Woodruff
    0.68
     Rockwell
    0.63
     vectorial
    0.62
     MTN
    0.62
     gebou
    0.61
    امة
    0.61
    Activations Density 0.214%

    No Known Activations