© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 1746
    Prev
    Next
    INDEX
    Explanations

    announcements and updates related to organizations or products

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

    Announcements or appointments

    np_acts-logits-general · gemini-2.0-flash

    official announcements and appointments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -1.03
     Efq
    -0.91
     Majefty
    -0.89
     greateſt
    -0.85
     AssemblyProduct
    -0.83
    mybatisplus
    -0.83
     Reſ
    -0.83
     ―――――
    -0.82
     Monfieur
    -0.80
     doubtnut
    -0.78
    POSITIVE LOGITS
     new
    0.51
    新しく
    0.46
     officially
    0.46
    新たに
    0.46
    新しい
    0.46
     announce
    0.45
     offiziell
    0.45
    新的
    0.44
     nuovo
    0.44
     named
    0.43
    Activations Density 0.226%

    No Known Activations