© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 13671
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a lower limit or minimal expectation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 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
     ferons
    -0.38
     travaillons
    -0.36
     vectorial
    -0.36
    voerd
    -0.35
     voyons
    -0.35
     História
    -0.34
    はじめに
    -0.33
     thousands
    -0.33
     crossorigin
    -0.33
    Autowired
    -0.33
    POSITIVE LOGITS
     least
    0.88
    Least
    0.88
    least
    0.84
     Least
    0.83
     atleast
    0.79
     LEAST
    0.77
    jmniej
    0.75
    poň
    0.75
     wenigstens
    0.74
     almeno
    0.71
    Activations Density 0.063%

    No Known Activations