© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 908
    Prev
    Next
    INDEX
    Explanations

    quotation marks and other punctuation associated with dialogue or speech

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

    Quotation marks followed by specific words

    np_acts-logits-general · gemini-2.0-flash

    quoted text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     ‘
    -1.08
     «
    -0.97
    ,
    -0.73
    )
    -0.65
    </h3>
    -0.65
    </h5>
    -0.64
     to
    -0.63
     and
    -0.61
     â
    -0.59
     da
    -0.58
    POSITIVE LOGITS
     pleaſure
    1.46
     purpoſe
    1.38
     ſtate
    1.36
     myſelf
    1.36
     greateſt
    1.34
     reaſon
    1.32
    .."
    1.26
    >"
    1.25
     leaſt
    1.24
     raiſ
    1.24
    Activations Density 0.252%

    No Known Activations