© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3903
    Prev
    Next
    INDEX
    Explanations

    instances of the word "from" and variations of it

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

    "From" at the beginning of sentences

    np_acts-logits-general · gemini-2.0-flash

    from a place or time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     они
    -0.53
     rospy
    -0.48
    깐
    -0.44
     вони
    -0.44
     он
    -0.43
     noastre
    -0.43
     вона
    -0.42
     она
    -0.42
    e
    -0.41
     він
    -0.41
    POSITIVE LOGITS
     afar
    1.39
     across
    1.23
     within
    1.20
     whence
    1.18
    within
    1.18
     scratch
    1.17
     abroad
    1.13
     elsewhere
    1.10
     EconPapers
    1.09
     anywhere
    1.08
    Activations Density 0.267%

    No Known Activations