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. 36-GEMMASCOPE-RES-16K
    6. 14808
    Prev
    Next
    INDEX
    Explanations

    terms related to illegality and corruption within financial systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     politiker
    -0.49
     policy
    -0.44
     ArrayAdapter
    -0.43
    verifyException
    -0.43
     piti
    -0.42
     चीज़ों
    -0.42
     Policy
    -0.41
     Normdatei
    -0.40
     actionMode
    -0.40
     consenso
    -0.39
    POSITIVE LOGITS
    rungsseite
    0.51
     genieten
    0.48
    ricle
    0.45
    
    0.45
     Estatal
    0.45
     süß
    0.43
     assimilated
    0.42
    
    0.42
     ziet
    0.42
     art
    0.42
    Activations Density 0.504%

    No Known Activations