© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12715
    Prev
    Next
    INDEX
    Explanations

    technical specifications and performance characteristics related to devices or systems

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

    numerical specifications and measurement ranges in technical texts.

    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
     language
    -0.27
     role
    -0.24
     involve
    -0.23
      
    -0.22
     involved
    -0.22
     đã
    -0.21
     entity
    -0.21
     collected
    -0.21
     encar
    -0.20
     meng
    -0.20
    POSITIVE LOGITS
     ModelExpression
    1.05
    twimg
    0.80
    AndEndTag
    0.79
     snippetHide
    0.76
     ویکی‌پدی
    0.74
     ujednoznacz
    0.74
     Normdatei
    0.73
    GOTREF
    0.71
    BufferException
    0.70
     PyLong
    0.69
    Activations Density 0.217%

    No Known Activations