© 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. 16-GEMMASCOPE-RES-16K
    11. 9645
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases related to fitting or accommodating within limited spaces

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

    putting things inside/into other things

    np_acts-logits-general · gemini-2.0-flash

    fit into or transmit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     led
    -0.44
    Unmarshaller
    -0.43
    ündete
    -0.43
     điệu
    -0.42
     Dy
    -0.41
    ảnh
    -0.41
     val
    -0.40
     jLabel
    -0.40
    val
    -0.40
    ene
    -0.39
    POSITIVE LOGITS
     accomplish
    0.84
     accomplishing
    0.74
     cram
    0.71
     accomplished
    0.71
     unfinished
    0.69
     productive
    0.68
     crammed
    0.66
     faſt
    0.65
     squeezed
    0.65
     chargeable
    0.63
    Activations Density 0.269%

    No Known Activations