© 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. 23-GEMMASCOPE-RES-16K
    11. 11505
    Prev
    Next
    INDEX
    Explanations

    references to the term "cat" in various contexts, particularly related to types of cathedrals and other religious or architectural references

    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
    Personendaten
    -0.67
     GenerationType
    -0.62
     ExecuteAsync
    -0.62
     vain
    -0.58
    djangoproject
    -0.57
    kháu
    -0.56
    Diweddarwch
    -0.56
    🏼
    -0.56
    RegressionTest
    -0.55
    didReceive
    -0.53
    POSITIVE LOGITS
     getCategory
    0.73
    agory
    0.72
    pillar
    0.63
    gory
    0.61
    hedrals
    0.61
    nip
    0.61
     wireType
    0.59
    lyst
    0.55
    |}{$
    0.55
     Meow
    0.54
    Activations Density 0.150%

    No Known Activations