© 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. 39-GEMMASCOPE-RES-16K
    11. 2887
    Prev
    Next
    INDEX
    Explanations

    sentences that convey emotional depth and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SuspendLayout
    -0.46
    evos
    -0.35
    +#+#
    -0.32
    ⤹
    -0.26
    /***/
    -0.26
     همان
    -0.25
    transQ
    -0.24
    [::-
    -0.24
     möge
    -0.24
    大型
    -0.24
    POSITIVE LOGITS
     excited
    1.70
     aware
    1.70
     fascinated
    1.64
     interested
    1.63
     pleased
    1.62
     afraid
    1.62
     amazed
    1.62
     thrilled
    1.59
     intrigued
    1.55
     willing
    1.54
    Activations Density 0.860%

    No Known Activations