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. 7212
    Prev
    Next
    INDEX
    Explanations

    the start of a new document or section

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

    Followed by a number

    np_acts-logits-general · gemini-2.0-flash

    foreign or archaic words

    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
    apimachinery
    -0.48
     over
    -0.47
    webElement
    -0.43
     sombras
    -0.43
    JsonKey
    -0.41
    omock
    -0.41
    过了
    -0.41
     once
    -0.40
    hifə
    -0.39
     sombra
    -0.38
    POSITIVE LOGITS
     Theſe
    0.92
     تانيه
    0.83
     متعلقه
    0.82
    Autoritní
    0.76
     myſelf
    0.73
     Houſe
    0.71
     Majefty
    0.70
     purpoſe
    0.70
     raiſ
    0.70
     ſtate
    0.69
    Activations Density 0.057%

    No Known Activations