© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4330
    Prev
    Next
    INDEX
    Explanations

    references to specific proteins involved in cellular signaling pathways

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

    molecular biology terms related to STAT signaling pathways and immune system cellular processes.

    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
    ReferenceEquals
    -0.54
    WebServlet
    -0.51
     EconPapers
    -0.51
     ब्रेकडाउन
    -0.50
    GraphicsUnit
    -0.48
     gynnwys
    -0.45
     ships
    -0.44
     Adult
    -0.41
     CURLOPT
    -0.40
     EnglishChoose
    -0.40
    POSITIVE LOGITS
     Italijani
    0.49
     صوتيه
    0.47
     يتيمه
    0.44
    cèse
    0.44
    orylation
    0.43
     phosphorylation
    0.42
     surla
    0.42
     aprende
    0.40
     журна
    0.39
     cascada
    0.39
    Activations Density 0.961%

    No Known Activations