Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 8465
    Prev
    Next
    INDEX
    Explanations

    expressions related to luck and fortune

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.58
    Derbyniad
    -0.58
    httphttps
    -0.55
     Савезне
    -0.54
     SwitchCompat
    -0.54
    rever
    -0.54
     comuniques
    -0.52
    >{@
    -0.52
     насељу
    -0.50
     CWE
    -0.50
    POSITIVE LOGITS
     fortunate
    1.41
     fortunately
    1.13
     Fortunately
    1.09
     lucky
    1.09
    Fortunately
    1.08
     Fortun
    1.04
     luckily
    1.02
    fortunate
    0.96
     Luckily
    0.95
    Luckily
    0.93
    Activations Density 0.282%

    No Known Activations