© 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. 18-GEMMASCOPE-RES-16K
    11. 15911
    Prev
    Next
    INDEX
    Explanations

    financial metrics and numerical data related to stock evaluations

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

    Content after "Let" keyword

    np_acts-logits-general · gemini-2.0-flash

    mathematical assignments and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ρίς
    -0.59
    intenance
    -0.51
    inafter
    -0.51
    couvrez
    -0.50
    σθαι
    -0.49
    atever
    -0.47
    клопе
    -0.47
     dolayı
    -0.46
    SQLiteDatabase
    -0.46
    Quoi
    -0.46
    POSITIVE LOGITS
     Exercise
    1.06
     exercise
    1.03
    Exercise
    0.96
    exercise
    0.95
     exercises
    0.92
     answer
    0.90
     Exercises
    0.89
    Exercises
    0.84
     questions
    0.83
     homework
    0.82
    Activations Density 0.824%

    No Known Activations