© 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. 15-GEMMASCOPE-RES-16K
    6. 11942
    Prev
    Next
    INDEX
    Explanations

    expressions of comparison or similarity, particularly with the word "like."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enterOuterAlt
    -0.56
     XNUMX
    -0.55
    parsedMessage
    -0.52
    ृत
    -0.49
     mať
    -0.47
    Otra
    -0.44
    另一种
    -0.44
    
    -0.43
     Otra
    -0.41
     another
    -0.40
    POSITIVE LOGITS
    RectangleBorder
    0.72
     seperti
    0.71
     telles
    0.71
     like
    0.71
    onAttach
    0.71
    IContainer
    0.70
     ***!
    0.70
     TableColumn
    0.69
     ourselves
    0.69
    omock
    0.67
    Activations Density 0.164%

    No Known Activations