© 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. 24-GEMMASCOPE-RES-16K
    6. 13492
    Prev
    Next
    INDEX
    Explanations

    terms related to proteins and their functions in cellular processes

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

    following a comma and related to biological processes or molecules

    np_acts-logits-general · gemini-2.0-flash

    proteins and genes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tartalomajánló
    -0.58
    colhead
    -0.51
     تكبرها
    -0.51
    IMON
    -0.51
     achtergrond
    -0.50
     ReSharper
    -0.49
    iric
    -0.48
     للاسماء
    -0.48
     дописавши
    -0.48
    ORATION
    -0.48
    POSITIVE LOGITS
     proteins
    1.28
     protein
    1.22
     Proteins
    1.06
     genes
    1.02
    proteins
    1.00
     Protein
    0.99
     enzymes
    0.99
    Proteins
    0.98
    protein
    0.98
    Protein
    0.91
    Activations Density 2.300%

    No Known Activations