© 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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15502
    Prev
    Next
    INDEX
    Explanations

    information related to temperature variations and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rối
    -0.57
     mascar
    -0.53
     кӀ
    -0.53
    falfa
    -0.52
    kész
    -0.50
    Kraft
    -0.49
    shortcode
    -0.49
    vatore
    -0.48
     Schlag
    -0.48
    ptonshire
    -0.48
    POSITIVE LOGITS
     temperature
    1.47
     temperatures
    1.46
    temperature
    1.42
     Temperatures
    1.41
     Temperature
    1.32
    Temperature
    1.25
     temperatura
    1.17
    TEMPERATURE
    1.16
     TEMPERATURE
    1.12
     temperatur
    1.10
    Activations Density 0.334%

    No Known Activations