© 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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 1812
    Prev
    Next
    INDEX
    Explanations

    words related to frameworks, foundations, and bases of arguments or systems

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

    Followed by prepositions like "to", "for", "in", or "of."

    np_acts-logits-general · gemini-2.0-flash

    basis, foundation, framework

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.64
    CompilerServices
    -0.63
    expandindo
    -0.61
    atimes
    -0.56
    PRNewswire
    -0.54
    vitis
    -0.53
    GroupLayout
    -0.52
     createSlice
    -0.52
    Rhestr
    -0.52
    Dış
    -0.52
    POSITIVE LOGITS
     betweenstory
    0.56
     framework
    0.53
     bagi
    0.52
    Reprodução
    0.50
     HttpHeaders
    0.48
     Frameworks
    0.48
    原始内容存档于
    0.48
     Framework
    0.48
    smöglichkeiten
    0.47
    ücken
    0.47
    Activations Density 0.540%

    No Known Activations