© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14950
    Prev
    Next
    INDEX
    Explanations

    references to radiation and its effects in various contexts

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

    starting with "Ir" or "IR"

    np_acts-logits-general · gemini-2.0-flash

    "Ir" or "IR" prefixes

    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
    ArgsConstructor
    -0.90
     للمعارف
    -0.89
     Unidas
    -0.81
    VolleyError
    -0.66
    ารถ
    -0.65
     ViewHolder
    -0.64
    ]")]
    -0.64
    hilation
    -0.64
    TagMode
    -0.63
    HomeAsUpEnabled
    -0.62
    POSITIVE LOGITS
     Ir
    0.88
     IR
    0.73
     ir
    0.71
    Ir
    0.64
     Iran
    0.59
    Iris
    0.59
     Iris
    0.56
     Irvin
    0.54
     irré
    0.51
    تاريخ
    0.51
    Activations Density 0.132%

    No Known Activations