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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 15143
    Prev
    Next
    INDEX
    Explanations

    references to biofuel production and related research

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

    associated with alternative energy sources

    np_acts-logits-general · gemini-2.0-flash

    biomass for energy and fuels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     voting
    -0.52
     paix
    -0.48
     voted
    -0.46
     sosp
    -0.46
     Surv
    -0.46
    BorderFactory
    -0.45
     Voted
    -0.45
    fail
    -0.45
    види
    -0.45
     gubern
    -0.44
    POSITIVE LOGITS
     valor
    0.85
     recovered
    0.79
     feed
    0.78
    valor
    0.77
     bio
    0.77
    recovered
    0.74
     Valor
    0.72
     biomass
    0.71
     recover
    0.71
     recovery
    0.70
    Activations Density 0.318%

    No Known Activations