© 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. 7675
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and sentiments towards experiences or evaluations

    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
     
    -1.68
    ,
    -1.58
     (
    -1.55
    .
    -1.48
    -
    -1.46
    1
    -1.42
    2
    -1.40
    ↵↵
    -1.39
    ↵
    -1.38
     in
    -1.37
    POSITIVE LOGITS
     desmotivaciones
    1.20
     étoient
    1.14
     avoient
    1.13
     étoit
    1.06
     feroit
    1.05
     auroit
    0.96
     pleaſure
    0.96
     pouvoit
    0.94
     pérd
    0.92
     miniaturka
    0.91
    Activations Density 17.417%

    No Known Activations