© 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. 15124
    Prev
    Next
    INDEX
    Explanations

    specific topics or concepts related to professional standards and regulations

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

    Follows "of" and precedes a word indicating importance

    np_acts-logits-general · gemini-2.0-flash

    indicating importance or consequence

    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
     ſtate
    -1.00
     houſe
    -0.96
     myſelf
    -0.93
     raiſ
    -0.90
     continúas
    -0.87
     ſta
    -0.87
     ſche
    -0.87
    ագրություններ
    -0.86
     poffe
    -0.86
     Majefty
    -0.86
    POSITIVE LOGITS
     
    0.52
     CreateTagHelper
    0.49
    </strong>
    0.44
    7
    0.44
    2
    0.43
    )
    0.43
     l
    0.43
    Đ
    0.42
    ”
    0.42
     p
    0.42
    Activations Density 0.483%

    No Known Activations