© 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. 5-GEMMASCOPE-RES-16K
    11. 9101
    Prev
    Next
    INDEX
    Explanations

    phrases indicating frequency or typical behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sprá
    -0.58
     braccia
    -0.56
     Clements
    -0.53
     terpisah
    -0.52
     Bringing
    -0.51
     شدند
    -0.51
     ней
    -0.51
     labios
    -0.50
    akt
    -0.50
     Building
    -0.49
    POSITIVE LOGITS
     usually
    1.91
     Usually
    1.81
    Usually
    1.77
    usually
    1.67
     typically
    1.53
     Typically
    1.51
    Typically
    1.50
     normally
    1.49
    normally
    1.46
    typically
    1.44
    Activations Density 0.153%

    No Known Activations