© 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. 14568
    Prev
    Next
    INDEX
    Explanations

    instructions or tips related to air conditioning and energy efficiency

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

    mentions of air conditioning systems and related components.

    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
    der
    -0.37
    ariamente
    -0.36
    ref
    -0.36
     Foer
    -0.35
    wer
    -0.35
    0
    -0.33
     chiunque
    -0.32
    en
    -0.31
     looser
    -0.31
    e
    -0.30
    POSITIVE LOGITS
     HVAC
    0.72
     houſe
    0.68
    HVAC
    0.68
     thermostat
    0.66
     myſelf
    0.64
     nakalista
    0.63
    MLLoader
    0.63
     kasarigan
    0.63
     ventilation
    0.61
    AnchorTagHelper
    0.61
    Activations Density 0.099%

    No Known Activations