© 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. 2-GEMMASCOPE-RES-16K
    6. 7180
    Prev
    Next
    INDEX
    Explanations

    quantitative relationships and dependencies in scientific or mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.50
     simplest
    -0.49
    )?;
    -0.47
    olis
    -0.47
    PHONY
    -0.46
     primary
    -0.45
    EndInit
    -0.45
    primary
    -0.45
    ]^{\
    -0.44
    ulet
    -0.44
    POSITIVE LOGITS
     value
    0.87
     values
    0.87
     valore
    0.83
     trị
    0.81
    SequentialGroup
    0.79
     Values
    0.78
     값
    0.77
     valeur
    0.75
     Value
    0.75
     nilai
    0.73
    Activations Density 1.109%

    No Known Activations