© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3234
    Prev
    Next
    INDEX
    Explanations

    biological terms related to viral constructs and mutations

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

    scientific/technical jargon, particularly related to molecular biology and virology (like specific gene or protein names, DNA/virus-related terminology).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     ainfi
    -0.69
     Económica
    -0.65
     neceſſ
    -0.64
     ſou
    -0.64
    ſelves
    -0.64
     myſelf
    -0.63
     auffi
    -0.62
     ſtand
    -0.62
    ActionCreators
    -0.62
     increí
    -0.61
    POSITIVE LOGITS
     D
    0.96
     d
    0.81
     DD
    0.80
     DMD
    0.71
     DM
    0.71
     DT
    0.69
     DV
    0.68
    D
    0.67
     DX
    0.67
     DQ
    0.66
    Activations Density 2.108%

    No Known Activations