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. 18-GEMMASCOPE-RES-16K
    6. 8507
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements and parameters related to scientific research

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

    Temperature values, often with exponents

    np_acts-logits-general · gemini-2.0-flash

    numerical temperature values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tartalomajánló
    -0.58
    Oneof
    -0.58
     définiti
    -0.57
     Heinemann
    -0.52
    Anonymous
    -0.50
     Languedoc
    -0.49
    radar
    -0.49
    kuš
    -0.49
    calypse
    -0.49
     Anonymous
    -0.48
    POSITIVE LOGITS
     temperature
    0.94
    temperature
    0.83
     Temperature
    0.79
    Temperature
    0.78
    cold
    0.78
     temperatures
    0.78
     warm
    0.77
     cold
    0.74
     Temperatures
    0.72
     temperatura
    0.71
    Activations Density 0.368%

    No Known Activations