© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 18-GEMMASCOPE-RES-16K
    11. 15043
    Prev
    Next
    INDEX
    Explanations

    instances of the word "for."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "For" followed by an example/explanation

    np_acts-logits-general · gemini-2.0-flash

    for followed by instance or example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.98
     CreateTagHelper
    -0.97
    ImageContext
    -0.91
     esternos
    -0.90
    CodeAttribute
    -0.90
    IonicModule
    -0.89
    XmlAccessType
    -0.89
    numerusform
    -0.85
    ResumeLayout
    -0.85
    Geplaatst
    -0.85
    POSITIVE LOGITS
     For
    0.77
    For
    0.77
     instance
    0.67
     for
    0.67
     example
    0.64
     years
    0.62
    cing
    0.56
     many
    0.56
     most
    0.55
     more
    0.54
    Activations Density 0.113%

    No Known Activations