© 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. 20-GEMMASCOPE-RES-16K
    6. 1136
    Prev
    Next
    INDEX
    Explanations

    phrases related to sequences or sequencing in a biological context

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

    "sequence"

    np_acts-logits-general · gemini-2.0-flash

    sequence analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.66
     embers
    -0.65
    MessageTagHelper
    -0.64
    YOND
    -0.63
    felves
    -0.62
    +};
    -0.60
    !("{
    -0.60
    yargs
    -0.59
    PhysRevD
    -0.58
    IsPostBack
    -0.58
    POSITIVE LOGITS
     sequences
    0.94
     seq
    0.89
     Sequences
    0.82
     Sequence
    0.81
     sequence
    0.74
    Sequences
    0.74
     sequ
    0.73
     SEQUENCE
    0.73
     Sequ
    0.72
    IUrlHelper
    0.71
    Activations Density 0.164%

    No Known Activations