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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 571
    Prev
    Next
    INDEX
    Explanations

    references to feelings of longing or nostalgia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     achieving
    -0.44
     Achieving
    -0.43
     doInBackground
    -0.42
    vVar
    -0.40
     ujednoznacz
    -0.39
    WebServlet
    -0.38
     parvenir
    -0.38
    AsUp
    -0.38
     portrayal
    -0.38
     bénéficier
    -0.38
    POSITIVE LOGITS
    把
    0.65
     put
    0.63
     entrust
    0.60
     send
    0.59
     allocate
    0.59
     направи
    0.57
     dedicate
    0.56
     hire
    0.56
     wysy
    0.55
     memasukkan
    0.54
    Activations Density 1.345%

    No Known Activations