© 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. 24-GEMMASCOPE-RES-16K
    11. 9620
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and numeric expressions

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

    Mathematical expressions involving multiplication

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions and numbers

    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
     might
    -1.75
    might
    -1.57
    Might
    -1.37
     Might
    -1.35
     MIGHT
    -1.00
     may
    -0.93
     potrebbe
    -0.74
     mungkin
    -0.73
    may
    -0.72
     potrebbero
    -0.70
    POSITIVE LOGITS
    يكب
    0.58
    sidemargin
    0.56
    ParallelGroup
    0.56
     XXV
    0.50
    berdayakan
    0.50
     twenty
    0.49
     XXIV
    0.49
     Дей
    0.49
    SBATCH
    0.49
    észetes
    0.48
    Activations Density 0.471%

    No Known Activations