© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 824
    Prev
    Next
    INDEX
    Explanations

    emphasis on the word "the" in various contexts, indicating its significance

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

    phrases related to having or possessing something.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered 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
    ,
    -0.39
     Streit
    -0.36
     gustos
    -0.35
     government
    -0.34
     there
    -0.33
     commerciales
    -0.32
    appendTo
    -0.32
    AP
    -0.32
     city
    -0.31
    B
    -0.31
    POSITIVE LOGITS
     nødven
    0.72
     FetchType
    0.69
    BibitemShut
    0.68
    principalColumn
    0.67
    IntoConstraints
    0.63
     lenker
    0.62
     necessary
    0.62
    iffance
    0.62
    pportun
    0.62
     ſich
    0.61
    Activations Density 0.188%

    No Known Activations