© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 2102
    Prev
    Next
    INDEX
    Explanations

    references to days of the week and dates

    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
    CppMethod
    -0.60
    omitempty
    -0.59
    AsStream
    -0.52
    Rigidbody
    -0.52
    cipais
    -0.51
    cydow
    -0.51
    nO
    -0.49
     ecto
    -0.49
    UINTN
    -0.49
     ArrayAdapter
    -0.49
    POSITIVE LOGITS
     Monday
    1.84
     Saturday
    1.84
     Tuesday
    1.81
     Wednesday
    1.81
     Friday
    1.79
     Sunday
    1.75
     Thursday
    1.74
    Saturday
    1.73
    Tuesday
    1.70
    Monday
    1.70
    Activations Density 0.166%

    No Known Activations