© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 2530
    Prev
    Next
    INDEX
    Explanations

    terms related to economic principles and mechanisms

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

    Follows adjectives like "valuable", "useful", or "costly"

    np_acts-logits-general · gemini-2.0-flash

    value and importance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     épaules
    -0.94
     lèvres
    -0.94
     négociations
    -0.82
     genoux
    -0.79
     dépens
    -0.79
     églises
    -0.78
     bienfaits
    -0.77
     attentes
    -0.76
     pouvoirs
    -0.75
     vœux
    -0.74
    POSITIVE LOGITS
     examples
    1.09
     entities
    1.05
     targets
    1.03
     substitutes
    1.02
     replacements
    1.02
     ones
    1.01
     extensions
    1.00
     objects
    0.99
     staples
    0.99
     additions
    0.98
    Activations Density 0.726%

    No Known Activations