© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 10900
    Prev
    Next
    INDEX
    Explanations

    references to cats and related terminology

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

    "Cat" or substrings within words

    np_acts-logits-general · gemini-2.0-flash

    cat and category

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    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
    -0.65
    Parcelize
    -0.62
    🏼
    -0.62
     mergeFrom
    -0.60
    StandardCharsets
    -0.59
    GraphicsUnit
    -0.59
    },[])
    -0.56
     ExecuteAsync
    -0.55
     }))
    -0.55
     newBuilder
    -0.54
    POSITIVE LOGITS
     getCategory
    1.19
     CAT
    1.05
     Cats
    1.04
     Cat
    1.02
     cats
    1.01
    Cats
    1.01
    Cat
    1.00
    CAT
    0.95
     Cata
    0.92
     cat
    0.91
    Activations Density 0.164%

    No Known Activations