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. 879
    Prev
    Next
    INDEX
    Explanations

    mentions of technology and its various applications and implications

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

    "technology"

    np_acts-logits-general · gemini-2.0-flash

    technology

    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
     ====
    -0.42
    —–
    -0.39
    orElse
    -0.39
    [:]
    -0.36
     Zuf
    -0.36
     الكريم
    -0.35
     sort
    -0.35
    ——–
    -0.34
     Ferrer
    -0.34
     Joey
    -0.34
    POSITIVE LOGITS
     Technology
    1.19
    Technology
    1.14
     technology
    1.13
    technology
    1.13
     Technol
    1.12
     technologie
    1.09
     TECHNOLOGY
    1.06
    TECHNOLOGY
    1.03
     Technolog
    1.02
     technologies
    0.99
    Activations Density 0.058%

    No Known Activations