© 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. 11-GEMMASCOPE-RES-16K
    11. 9081
    Prev
    Next
    INDEX
    Explanations

    narrative elements involving personal struggles and emotional states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    actory
    -0.35
    ɵɵ
    -0.34
    Népesség
    -0.33
     colectiva
    -0.33
     féd
    -0.32
     contemporánea
    -0.32
     Berufs
    -0.32
    zty
    -0.31
     surla
    -0.31
    inary
    -0.31
    POSITIVE LOGITS
     estekak
    0.56
     carrying
    0.56
    帶著
    0.55
    Carrying
    0.55
     Carrying
    0.55
     membawa
    0.54
    carrying
    0.50
    脚注の使い方
    0.49
     armed
    0.49
     Carry
    0.49
    Activations Density 0.446%

    No Known Activations