© 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. 16-GEMMASCOPE-RES-16K
    11. 9495
    Prev
    Next
    INDEX
    Explanations

    sections of text that contain no significant content or activation signals

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

    Funding or grants

    np_acts-logits-general · gemini-2.0-flash

    NSF grants and funding

    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
     never
    -0.46
     cho
    -0.45
     unos
    -0.43
     almost
    -0.42
     절
    -0.40
     un
    -0.40
    |}{}
    -0.39
     nearly
    -0.39
     prat
    -0.37
    agh
    -0.37
    POSITIVE LOGITS
     betweenstory
    1.11
    følgelig
    0.93
    ьаж
    0.89
     grants
    0.85
     grant
    0.84
     funded
    0.82
     विश्वसनीयता
    0.79
     funding
    0.78
    grant
    0.76
    Grant
    0.76
    Activations Density 0.306%

    No Known Activations