© 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. 37-GEMMASCOPE-RES-16K
    11. 3171
    Prev
    Next
    INDEX
    Explanations

    phrases related to the first person, particularly pronouns and possessives in Spanish

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forhold
    -1.00
     mystère
    -0.91
     drapeau
    -0.90
     vœ
    -0.89
    føre
    -0.86
     vêtement
    -0.85
    miljø
    -0.84
     doigt
    -0.84
     lendemain
    -0.82
    løs
    -0.81
    POSITIVE LOGITS
    Är
    0.40
     στιγ
    0.40
    cheibe
    0.37
     مج
    0.36
    宣
    0.36
    FFER
    0.36
     betrekking
    0.34
     Bischof
    0.34
    balho
    0.33
     חיצוניים
    0.33
    Activations Density 0.057%

    No Known Activations