© 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-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 9295
    Prev
    Next
    INDEX
    Explanations

    concepts related to thermodynamics and energy exchange processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defStyle
    -0.53
    edicated
    -0.51
     ModelExpression
    -0.50
    Xna
    -0.48
     putus
    -0.47
    optionalTypeArgs
    -0.46
     препратки
    -0.45
    GEBURTSDATUM
    -0.44
    GeneratedCode
    -0.44
     Italijanski
    -0.43
    POSITIVE LOGITS
     adiabatic
    0.60
     thermodynamic
    0.60
     autorytatywna
    0.57
     pressure
    0.54
    Pressure
    0.51
    熵
    0.51
     pressures
    0.51
     compression
    0.49
    Entropy
    0.49
    pressure
    0.49
    Activations Density 0.640%

    No Known Activations