© 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. 20-GEMMASCOPE-RES-16K
    6. 16202
    Prev
    Next
    INDEX
    Explanations

    terms related to heating and temperature control systems

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

    automatic control systems with sensors that regulate temperature, pressure, or fluid levels.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     становника
    -0.56
     outsider
    -0.48
    ፩
    -0.48
    发表于
    -0.48
     fum
    -0.46
    笼
    -0.45
    袈
    -0.45
    }}/>
    -0.45
    ̸
    -0.44
     насељу
    -0.44
    POSITIVE LOGITS
     automático
    0.57
    adaptive
    0.52
     WebDriverWait
    0.52
    automatic
    0.51
     automatico
    0.48
     adaptive
    0.48
     sää
    0.48
    自动
    0.47
    autom
    0.47
    automatically
    0.47
    Activations Density 0.516%

    No Known Activations