© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10678
    Prev
    Next
    INDEX
    Explanations

    instances of tab-separated values or numerical data

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

    Tokens preceding numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers and symbols

    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
     betweenstory
    -0.70
    setVerticalGroup
    -0.66
     Numerade
    -0.63
    fromnode
    -0.62
    rungsseite
    -0.62
     otomatig
    -0.61
     indígen
    -0.60
    HomeAsUpEnabled
    -0.60
    تقاوى
    -0.60
     CreateTagHelper
    -0.60
    POSITIVE LOGITS
    <bos>
    0.73
    The
    0.57
     the
    0.53
    Pal
    0.49
    the
    0.48
     
    0.48
    Mus
    0.47
     Mus
    0.45
    Tro
    0.45
    Ru
    0.45
    Activations Density 1.678%

    No Known Activations