© 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. 7098
    Prev
    Next
    INDEX
    Explanations

    connections between various concepts or elements

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

    Legal or factual allegations and evidence

    np_acts-logits-general · gemini-2.0-flash

    allegations, statutes, evidence, pursuant

    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
     atitude
    -0.49
     favours
    -0.48
    oficial
    -0.48
     guys
    -0.47
    HasAnnotation
    -0.47
    igh
    -0.46
     FREE
    -0.45
     humain
    -0.45
     rigs
    -0.45
     slows
    -0.44
    POSITIVE LOGITS
     pursuant
    0.85
     purported
    0.71
     ejus
    0.71
     contemporaneous
    0.68
    ulitis
    0.66
    oweit
    0.66
     substantially
    0.65
     nunmehr
    0.63
     allegedly
    0.62
     poveznice
    0.62
    Activations Density 6.623%

    No Known Activations