© 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 - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 496
    Prev
    Next
    INDEX
    Explanations

    existential and emotional concerns related to personal well-being and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    excessive worry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GTCX
    -0.41
    ########.
    -0.38
     both
    -0.36
     recensement
    -0.36
     purpoſe
    -0.36
    が存在
    -0.35
     благода
    -0.35
     zowel
    -0.35
    ValueStyle
    -0.35
    épendance
    -0.35
    POSITIVE LOGITS
     worries
    0.51
     kaarangay
    0.51
     незавершена
    0.50
     bothers
    0.50
     terlalu
    0.50
     unwanted
    0.50
     disliked
    0.47
    ftagPool
    0.47
     zbyt
    0.46
     bothering
    0.46
    Activations Density 0.040%

    No Known Activations