© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 5828
    Prev
    Next
    INDEX
    Explanations

    references to file types and data formats

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

    Tokens followed by numbers or special characters

    np_acts-logits-general · gemini-2.0-flash

    Raman spectroscopy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     well
    -0.30
     kennt
    -0.24
    ं
    -0.23
     yet
    -0.23
     it
    -0.23
     can
    -0.22
     almost
    -0.22
     personal
    -0.22
     good
    -0.21
     next
    -0.21
    POSITIVE LOGITS
    MessageOf
    0.92
    expandindo
    0.83
     queſta
    0.81
    :✨
    0.81
    
    0.79
     INTERESAR
    0.78
     Paglinawan
    0.75
     esternos
    0.74
    <unused47>
    0.73
    [@BOS@]
    0.73
    Activations Density 0.527%

    No Known Activations