© 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. 22-GEMMASCOPE-RES-16K
    11. 5718
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and relationship dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quelquefois
    -0.56
     wußte
    -0.56
     ilustracja
    -0.54
     bowiem
    -0.48
     occorre
    -0.47
     muß
    -0.44
     müßte
    -0.44
     pertanto
    -0.44
     Signalez
    -0.43
    יצד
    -0.43
    POSITIVE LOGITS
     shitty
    0.90
     fuck
    0.87
     fucked
    0.86
     idk
    0.83
     fuckin
    0.82
     fucking
    0.82
    fuck
    0.81
     tryna
    0.80
     bullshit
    0.79
     FUCK
    0.77
    Activations Density 0.643%

    No Known Activations