© 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. 28-GEMMASCOPE-RES-16K
    6. 7778
    Prev
    Next
    INDEX
    Explanations

    terms related to energy efficiency and modern lighting technology

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

    lighting

    np_acts-logits-general · gemini-2.0-flash

    illumination and light

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     []:
    -0.30
     Tsch
    -0.25
    dolo
    -0.24
     Hutchinson
    -0.24
     fér
    -0.24
     inter
    -0.24
     Lieben
    -0.24
     것
    -0.24
     maternal
    -0.23
     erop
    -0.23
    POSITIVE LOGITS
     LEDs
    1.16
     lighting
    1.16
     LED
    1.15
     lights
    1.12
     lamps
    1.11
     illumination
    1.09
     Lighting
    1.09
    Lighting
    1.07
     lamp
    1.05
     lampu
    1.04
    Activations Density 0.293%

    No Known Activations