Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 6300
    Prev
    Next
    INDEX
    Explanations

    concepts related to thermodynamics and energy transfer

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Traffic
    -0.60
    Traffic
    -0.60
     TRAFFIC
    -0.56
     traffic
    -0.55
    intf
    -0.55
    rifuge
    -0.51
    antaine
    -0.51
     foule
    -0.50
     vertreten
    -0.49
    Growing
    -0.49
    POSITIVE LOGITS
     energy
    0.96
    energy
    0.85
     Energies
    0.81
     energies
    0.79
     Energy
    0.78
    ENERGY
    0.78
    ########.
    0.77
    Energy
    0.74
     energie
    0.74
     énergie
    0.74
    Activations Density 0.311%

    No Known Activations