© 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. 3-GEMMASCOPE-RES-16K
    6. 9681
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and variables related to constants and coefficients in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </em>
    -0.51
    U
    -0.48
     U
    -0.46
    ino
    -0.45
     fu
    -0.44
     “
    -0.44
    MouseUp
    -0.43
     "
    -0.43
    burgh
    -0.43
     Open
    -0.43
    POSITIVE LOGITS
    windowFixed
    1.06
    TargetException
    1.03
    RegressionTest
    0.91
    tagext
    0.91
    AndEndTag
    0.87
     MainAxisSize
    0.86
     Roskov
    0.85
    InputBorder
    0.84
    SharedCtor
    0.81
    StructEnd
    0.81
    Activations Density 1.056%

    No Known Activations