© 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. 15298
    Prev
    Next
    INDEX
    Explanations

    expressions of hope and positive reassurance during difficult times

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

    Following "to", "just", "doing", or "is"

    np_acts-logits-general · gemini-2.0-flash

    things are alright

    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
    AddHtmlAttribute
    -0.66
     Exacts
    -0.64
    reszcie
    -0.59
    setAccessible
    -0.57
     Exactos
    -0.56
     Infórmanos
    -0.55
     оригіналу
    -0.54
    发表于
    -0.53
    SharedDtor
    -0.53
    Читати
    -0.52
    POSITIVE LOGITS
     OK
    1.98
     ok
    1.94
     okay
    1.78
    OK
    1.65
     alright
    1.64
    Ok
    1.52
     Ok
    1.50
    okay
    1.44
     OKAY
    1.40
    ok
    1.38
    Activations Density 0.173%

    No Known Activations