© 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-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 13096
    Prev
    Next
    INDEX
    Explanations

    elements of dark humor and irony in writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    liosis
    -0.62
    WICK
    -0.58
    ännande
    -0.55
    ริง
    -0.53
     fusca
    -0.52
    #
    -0.51
    ⛧
    -0.51
     pís
    -0.51
    createStatement
    -0.51
    arbox
    -0.50
    POSITIVE LOGITS
     contrived
    0.97
     cheesy
    0.94
     tacky
    0.90
     clich
    0.86
     clic
    0.85
     bland
    0.83
     cliche
    0.82
     gratuitous
    0.82
     overly
    0.80
     predictable
    0.79
    Activations Density 0.366%

    No Known Activations