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-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 2801
    Prev
    Next
    INDEX
    Explanations

    language related to legal and governmental qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     incentiv
    -0.94
     impactful
    -0.93
     toolkit
    -0.92
     behaviors
    -0.86
     proactively
    -0.85
     sourced
    -0.85
     prioritize
    -0.85
     prioriti
    -0.82
     timeframe
    -0.79
     flipped
    -0.78
    POSITIVE LOGITS
     skall
    0.98
     muß
    0.86
     daß
    0.85
     giebt
    0.84
     enfans
    0.83
    faßt
    0.82
     mußte
    0.77
     läßt
    0.75
     müßte
    0.73
     mußten
    0.72
    Activations Density 4.794%

    No Known Activations