© 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. 1-GEMMASCOPE-RES-16K
    6. 7455
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating differences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſp
    -0.56
     ſy
    -0.54
    zell
    -0.52
    inhos
    -0.51
    oj
    -0.50
    רושלים
    -0.50
     pade
    -0.50
     Samar
    -0.49
    ContentValues
    -0.49
     Barbuda
    -0.48
    POSITIVE LOGITS
     than
    4.37
     THAN
    3.77
    Than
    3.37
     Than
    3.26
    than
    3.23
     niż
    2.96
    THAN
    2.76
     än
    2.51
     decât
    2.43
     než
    2.32
    Activations Density 0.112%

    No Known Activations