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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 3652
    Prev
    Next
    INDEX
    Explanations

    information related to plant viruses and their host preferences

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

    Biological families, especially plant families

    np_acts-logits-general · gemini-2.0-flash

    biological family or order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.74
     оригіналу
    -0.73
    SharedCtor
    -0.70
    matchCondition
    -0.67
    Revenir
    -0.64
    FileVersion
    -0.64
    !("{}",
    -0.64
    arraycopy
    -0.60
     الاطلاع
    -0.60
    WriteTagHelper
    -0.59
    POSITIVE LOGITS
     family
    1.07
     Family
    0.99
    family
    0.99
    Family
    0.95
     FAMILY
    0.89
     famiglia
    0.78
    FAMILY
    0.75
     Families
    0.75
     order
    0.75
     families
    0.75
    Activations Density 0.452%

    No Known Activations