© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13999
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and biochemical terminology

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

    This neuron detects chemical compounds and organic substances, including body tissues, foods, and biological molecules.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
    fjspx
    -0.55
    parsedMessage
    -0.47
    umumkan
    -0.45
     lenker
    -0.44
    udesta
    -0.44
     membuk
    -0.44
     pitä
    -0.43
    occasione
    -0.42
     eccell
    -0.42
    antaranya
    -0.42
    POSITIVE LOGITS
     ſte
    0.57
     air
    0.52
     fecond
    0.52
     Rigidbody
    0.52
     electric
    0.52
     mobile
    0.49
     chemical
    0.48
     tennis
    0.48
     financial
    0.48
    urlencoded
    0.48
    Activations Density 1.040%

    No Known Activations