© 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. 1-GEMMASCOPE-RES-16K
    11. 9566
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "az" and its derivatives, likely indicating colloquial or informal expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enfance
    -0.60
    hygiène
    -0.57
    humanité
    -0.55
    épaisseur
    -0.55
    entretien
    -0.55
    éclairage
    -0.54
    interprétation
    -0.53
    humidité
    -0.52
    amitié
    -0.52
    essentiel
    -0.52
    POSITIVE LOGITS
    az
    1.24
    away
    1.20
    ax
    1.16
    aw
    1.13
    av
    1.12
    af
    1.12
    ab
    1.11
    ap
    1.11
    ah
    1.09
    aj
    1.09
    Activations Density 0.693%

    No Known Activations