© 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. 33-GEMMASCOPE-RES-16K
    11. 7942
    Prev
    Next
    INDEX
    Explanations

    terms related to personal experiences and interactions, particularly those reflecting opinions and emotions

    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
     cannot
    -0.77
    Cannot
    -0.74
    cannot
    -0.73
     Cannot
    -0.69
     sahiptir
    -0.54
     אנו
    -0.51
    ですので
    -0.49
    mektedir
    -0.47
    maktadır
    -0.46
     egli
    -0.45
    POSITIVE LOGITS
     isn
    1.59
     aren
    1.51
     shouldn
    1.34
     weren
    1.32
     wasn
    1.31
     hasn
    1.31
     wouldn
    1.29
     didn
    1.26
     doesn
    1.25
    doesn
    1.25
    Activations Density 0.484%

    No Known Activations