© 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. 23-GEMMASCOPE-RES-16K
    11. 367
    Prev
    Next
    INDEX
    Explanations

    demographic indicators related to gender and nationality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 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
    estacks
    -0.58
     estekak
    -0.55
    fromCharCode
    -0.51
    mær
    -0.51
    ########.
    -0.50
     klubben
    -0.50
    saraba
    -0.49
    bootstrapcdn
    -0.49
     renovables
    -0.48
    Atsauces
    -0.47
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.50
     statistical
    0.43
     resourceCulture
    0.43
    httphttps
    0.42
     statistically
    0.41
     outliers
    0.41
     Vec
    0.40
     TimeUnit
    0.39
     IUser
    0.38
     userEmail
    0.38
    Activations Density 0.704%

    No Known Activations