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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 779
    Prev
    Next
    INDEX
    Explanations

    issues related to excess and over-indulgence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding "too" and indicating excessiveness

    np_acts-logits-general · gemini-2.0-flash

    excessive or too much

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndroidJUnit
    -0.45
     utafitiHapana
    -0.40
    мін
    -0.36
    srcs
    -0.36
    المناصب
    -0.35
    `.`
    -0.34
    reuters
    -0.34
    Vidi
    -0.34
     önemli
    -0.33
    Raymond
    -0.33
    POSITIVE LOGITS
     excessive
    1.05
    Excessive
    1.00
     Excessive
    0.98
     exces
    0.97
    过度
    0.96
     excessively
    0.94
     overkill
    0.93
     overly
    0.90
     exceso
    0.90
     TOO
    0.85
    Activations Density 0.407%

    No Known Activations