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. 41-GEMMASCOPE-RES-16K
    6. 7272
    Prev
    Next
    INDEX
    Explanations

    references to notable authors and their works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.45
    principalColumn
    -0.39
    AndroidJUnit
    -0.39
    Personensuche
    -0.38
     Infórmanos
    -0.38
    ernoo
    -0.36
     चीज़ों
    -0.35
    GEBURTS
    -0.35
    今まで
    -0.35
    èlement
    -0.35
    POSITIVE LOGITS
     observed
    0.79
     observes
    0.77
     observing
    0.70
     summed
    0.70
     aptly
    0.68
     observe
    0.68
    Observed
    0.64
     Observing
    0.63
     observation
    0.63
     osserv
    0.63
    Activations Density 0.561%

    No Known Activations