© 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. 33-GEMMASCOPE-RES-16K
    11. 10175
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the" as a definite article

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oader
    -0.44
    Datuak
    -0.37
    dicionado
    -0.36
    argout
    -0.35
    ものである
    -0.35
     GENERATED
    -0.35
    rosted
    -0.35
    ########.
    -0.35
    libft
    -0.34
    skou
    -0.34
    POSITIVE LOGITS
     midst
    1.12
     meantime
    1.05
     absence
    0.96
     vicinity
    0.90
     context
    0.90
     wake
    0.89
     actualidad
    0.83
     guise
    0.78
     meanwhile
    0.73
     aftermath
    0.72
    Activations Density 0.551%

    No Known Activations