© 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. 15640
    Prev
    Next
    INDEX
    Explanations

    sentiments related to feelings of hurt, regret, and the evaluation of experiences

    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
    expandindo
    -0.52
    تقاوى
    -0.44
     gynhyrchwyd
    -0.42
     виправивши
    -0.40
    ilton
    -0.39
    enschappelijke
    -0.39
    opsida
    -0.39
    dafx
    -0.38
     Chwiliwch
    -0.38
    ẖ
    -0.37
    POSITIVE LOGITS
     whatsoever
    1.87
     affatto
    1.31
     vůbec
    1.13
     כלל
    1.07
     alls
    1.02
     вовсе
    0.96
    soever
    0.92
     AT
    0.89
     absoluto
    0.88
     בכל
    0.85
    Activations Density 0.335%

    No Known Activations