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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8367
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to molecular biology and genetic analysis

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

    Amino acids, exons, codons, and regions in proteins

    np_acts-logits-general · gemini-2.0-flash

    amino-terminal regions and sequences

    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
    AutoScaleMode
    -0.76
    BagLayout
    -0.70
    ỡng
    -0.68
    parsedMessage
    -0.60
    jgl
    -0.58
    Jereo
    -0.56
     Packages
    -0.56
     packages
    -0.56
    package
    -0.54
    styleType
    -0.54
    POSITIVE LOGITS
     region
    0.76
    region
    0.71
     conserved
    0.71
     sequence
    0.71
     residues
    0.65
    Region
    0.64
     sequences
    0.62
     regions
    0.61
     consensus
    0.61
    gion
    0.59
    Activations Density 1.794%

    No Known Activations