© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 13229
    Prev
    Next
    INDEX
    Explanations

    mentions of emotional connections and relationships, particularly those surrounding loss and familial ties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    彼は
    -0.71
    的他
    -0.69
     his
    -0.66
     jeho
    -0.65
     hans
    -0.64
    His
    -0.62
     boyhood
    -0.62
    his
    -0.62
     dets
    -0.59
    彼の
    -0.59
    POSITIVE LOGITS
     herself
    2.52
    herself
    1.94
     her
    1.50
     suaminya
    1.31
     그녀
    1.27
    她的
    1.27
     hennes
    1.25
     její
    1.21
    彼女は
    1.16
    彼女の
    1.16
    Activations Density 0.908%

    No Known Activations