Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8537
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms related to ion transport mechanisms

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

    Ion channels and transmembrane proteins

    np_acts-logits-general · gemini-2.0-flash

    sodium, salt, and ion transport

    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
    Życiorys
    -0.52
    estacks
    -0.52
    NewGuid
    -0.51
     Metzger
    -0.47
    UserScript
    -0.47
    !("{
    -0.46
     nahilalakip
    -0.46
    !("{}",
    -0.45
     AssemblyProduct
    -0.45
    enerys
    -0.44
    POSITIVE LOGITS
     salt
    1.10
     sodium
    1.07
     osmotic
    1.00
     Sodium
    0.99
     ions
    0.97
    salt
    0.97
    sodium
    0.97
     Salt
    0.96
    Salt
    0.95
     ion
    0.94
    Activations Density 0.871%

    No Known Activations