© 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. 2-GEMMASCOPE-RES-16K
    11. 4036
    Prev
    Next
    INDEX
    Explanations

    references to energy-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Revis
    -0.65
    govine
    -0.61
    setImageBitmap
    -0.61
     déchir
    -0.60
    cko
    -0.59
    chitis
    -0.59
    chtenstein
    -0.59
    excellents
    -0.58
     mattino
    -0.58
     convain
    -0.57
    POSITIVE LOGITS
     energy
    3.65
     Energy
    3.35
    energy
    3.27
    Energy
    3.15
     ENERGY
    3.12
    ENERGY
    2.86
     energies
    2.60
     energia
    2.26
     Energies
    2.22
     Energie
    2.20
    Activations Density 0.058%

    No Known Activations