© 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. 38-GEMMASCOPE-RES-16K
    11. 13532
    Prev
    Next
    INDEX
    Explanations

    comparisons between prominent business figures and their different approaches or philosophies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagext
    -0.52
     neumáticos
    -0.44
    liceerd
    -0.43
    IBOutlet
    -0.43
     Verstär
    -0.43
     Verwenden
    -0.43
     Olivenöl
    -0.42
     Ausrüstung
    -0.42
     OnTriggerEnter
    -0.42
    mybatisplus
    -0.42
    POSITIVE LOGITS
     Silicon
    0.91
     Alphabet
    0.81
    Silicon
    0.77
     CEO
    0.77
     Musk
    0.76
     Tesla
    0.72
     CEOs
    0.72
    硅
    0.72
     Facebook
    0.72
     Elon
    0.71
    Activations Density 0.637%

    No Known Activations