Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9780
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "design" and related phrases

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

    "design"

    np_acts-logits-general · gemini-2.0-flash

    design

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     terceiros
    -0.52
     bancaire
    -0.50
     hodiny
    -0.48
     Whittaker
    -0.47
     sesama
    -0.47
     dormitórios
    -0.47
     innymi
    -0.46
    thenReturn
    -0.46
     parachoque
    -0.46
     retVal
    -0.46
    POSITIVE LOGITS
     design
    1.30
     Design
    1.23
    Design
    1.16
     DESIGN
    1.12
    design
    1.09
    DESIGN
    1.05
     designs
    1.03
     diseño
    0.98
    设计
    0.98
     Designs
    0.98
    Activations Density 0.053%

    No Known Activations