© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 38-GEMMASCOPE-RES-16K
    11. 15051
    Prev
    Next
    INDEX
    Explanations

    terms related to mental states, emotions, and health conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    舺
    -0.39
     hâte
    -0.37
     convince
    -0.34
     hadas
    -0.34
     tört
    -0.33
     çıktı
    -0.32
     rése
    -0.32
     dévelo
    -0.32
     çı
    -0.31
    contentLoaded
    -0.30
    POSITIVE LOGITS
    defining
    1.10
    ifying
    1.10
     consuming
    1.09
    controlling
    1.09
    tifying
    1.09
     destroying
    1.05
    generating
    1.04
     defining
    1.03
     enhancing
    1.03
     generating
    1.02
    Activations Density 1.375%

    No Known Activations