Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 91554
    Prev
    Next
    INDEX
    Explanations

    instances of end-of-turn markers in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Geh
    -0.37
    twimg
    -0.36
    font
    -0.34
     humour
    -0.34
     font
    -0.33
     symbolic
    -0.33
     stretch
    -0.33
    alchemy
    -0.32
    JMenuBar
    -0.31
     dieux
    -0.31
    POSITIVE LOGITS
    SourceChecksum
    0.73
     незавершена
    0.65
    tagHelperRunner
    0.65
    ">//
    0.62
     يتيمه
    0.59
    ंदीखरीदारी
    0.58
     <<<<<<<<<<<<<<
    0.58
    GTCX
    0.57
     ProtoMessage
    0.57
     المعيارى
    0.55
    Activations Density 0.067%

    No Known Activations