© 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. 0-GEMMASCOPE-RES-16K
    11. 2978
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "undertake" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sanciones
    -0.69
     cooperación
    -0.67
     exportación
    -0.64
     normalidad
    -0.64
     prestaciones
    -0.62
     recomendaciones
    -0.61
     sugerencias
    -0.60
     garantías
    -0.60
     transparencia
    -0.59
     novedades
    -0.59
    POSITIVE LOGITS
     stories
    1.07
     Stories
    0.92
     storytelling
    0.91
     conversations
    0.88
    conversations
    0.84
     Telling
    0.84
     episodes
    0.83
     Sessions
    0.83
    Stories
    0.82
     Conversations
    0.82
    Activations Density 0.229%

    No Known Activations