© 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. 25-GEMMASCOPE-RES-16K
    11. 2508
    Prev
    Next
    INDEX
    Explanations

    terms related to thermodynamic laws and energy changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.63
     làng
    -0.51
     Silverman
    -0.51
     JpaRepository
    -0.51
    utivo
    -0.51
     Gentiles
    -0.51
     Chorus
    -0.49
    ObjectMeta
    -0.48
     Boc
    -0.48
     הארץ
    -0.48
    POSITIVE LOGITS
     energy
    1.49
     Energy
    1.31
    energy
    1.28
    Energy
    1.28
     ENERGY
    1.18
    ENERGY
    1.08
     energies
    1.06
     Energies
    1.00
     Energie
    0.99
    énergie
    0.99
    Activations Density 0.930%

    No Known Activations