© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 24018
    Prev
    Next
    INDEX
    Explanations

    terms related to gravitational energy and potential in physical systems

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

    minimize potential energy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    weakSelf
    -0.37
    idemiology
    -0.32
     hearing
    -0.31
     Hearing
    -0.30
    honneur
    -0.30
    impresa
    -0.29
     hoor
    -0.29
     document
    -0.29
     Hör
    -0.28
     Pollut
    -0.28
    POSITIVE LOGITS
     energy
    1.09
    Potential
    1.07
     potential
    1.06
     Potential
    1.05
    potential
    1.04
     energía
    1.03
     énergie
    1.00
     POTENTIAL
    0.98
     energia
    0.97
     kinetic
    0.94
    Activations Density 0.184%

    No Known Activations