© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8082
    Prev
    Next
    INDEX
    Explanations

    references to temperature in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.40
     ErrIntOverflow
    -0.39
     Werke
    -0.37
    UnusedPrivate
    -0.37
     menyus
    -0.36
    <bos>
    -0.35
     <>",
    -0.34
    hbs
    -0.34
    Geografie
    -0.34
    hyrchwyd
    -0.33
    POSITIVE LOGITS
     temperature
    2.17
     Temperature
    2.05
     temperatures
    2.03
    Temperature
    1.95
    temperature
    1.91
     Temperatures
    1.84
     TEMPERATURE
    1.82
     Temp
    1.80
     temp
    1.80
     température
    1.63
    Activations Density 0.110%

    No Known Activations