© 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. 20-GEMMASCOPE-RES-16K
    6. 2208
    Prev
    Next
    INDEX
    Explanations

    scientific terminology and language related to research objectives

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

    scientific and technical language related to research, technology, and professional contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    This neuron identifies the introduction or purpose sections of academic papers and formal documents, often activating on phrases like "the aim of this study" or "this information will be important".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     ویکی‌پدی
    -0.41
     <>",
    -0.40
    memoized
    -0.40
    TemporalType
    -0.40
    Bibliograf
    -0.38
    SourceChecksum
    -0.38
     SIMBAD
    -0.37
    PullParser
    -0.36
    PROTOBUF
    -0.35
     skolan
    -0.35
    POSITIVE LOGITS
    
    0.54
    قایناق‌لار
    0.53
     EconPapers
    0.52
    ⤹
    0.48
     resource
    0.45
     petal
    0.44
    ंदीखरीदारी
    0.44
     fashiola
    0.44
     jScrollPane
    0.43
     prohibido
    0.43
    Activations Density 0.545%

    No Known Activations