© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 7440
    Prev
    Next
    INDEX
    Explanations

    repeated occurrences of the word "frequent."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.63
     ujednoznacz
    -0.59
    ########.
    -0.57
     mergeFrom
    -0.54
     disambiguazione
    -0.52
    ISupport
    -0.52
     GenerationType
    -0.49
    AnimationsModule
    -0.48
    errHandler
    -0.47
    habits
    -0.47
    POSITIVE LOGITS
     frequent
    1.14
     Frequent
    0.92
    frequent
    0.91
    Frequent
    0.89
     extended
    0.79
     occasional
    0.73
     repeated
    0.73
     periodic
    0.69
    extended
    0.68
    Repeated
    0.61
    Activations Density 0.080%

    No Known Activations