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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1842
    Prev
    Next
    INDEX
    Explanations

    phrases related to wastefulness and productivity loss

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fortawesome
    -0.58
    ساب
    -0.50
    atars
    -0.49
    joba
    -0.48
     تط
    -0.46
    ulman
    -0.46
    gares
    -0.46
    verhält
    -0.45
    jetas
    -0.45
     newly
    -0.45
    POSITIVE LOGITS
     wasted
    0.98
     wastes
    0.81
     unproductive
    0.80
     wasting
    0.79
     unnecessarily
    0.77
     needlessly
    0.77
     myſelf
    0.72
     avoidable
    0.70
    ^(@)
    0.70
    AnchorStyles
    0.69
    Activations Density 0.247%

    No Known Activations