© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 13021
    Prev
    Next
    INDEX
    Explanations

    references to sports figures and their biographies

    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
    IndentedString
    -0.63
    IntoConstraints
    -0.56
    featureID
    -0.50
     فريبيس
    -0.46
    Sucesor
    -0.45
     queſta
    -0.42
    yntaxException
    -0.42
     asupra
    -0.41
    Personensuche
    -0.40
    SBATCH
    -0.40
    POSITIVE LOGITS
    (...)
    0.44
    Template
    0.42
    '));
    0.42
    ########.
    0.41
     Wikip
    0.41
    :✨
    0.40
     wikipedia
    0.39
    "));
    0.39
     Wikipedia
    0.39
    [...]
    0.37
    Activations Density 0.463%

    No Known Activations