© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14401
    Prev
    Next
    INDEX
    Explanations

    references to reconstruction methods and their performance in data analysis

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

    scientific or technical methodology discussions with terms related to statistical models and reconstruction methods.

    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
    
    -0.79
    GEBURTSDATUM
    -0.79
     Photocase
    -0.65
    Datuak
    -0.63
     للاسماء
    -0.60
     validamos
    -0.59
     Catawiki
    -0.57
     queſta
    -0.57
    addContainerGap
    -0.56
    ChildScrollView
    -0.56
    POSITIVE LOGITS
     method
    0.45
     methods
    0.41
     resolution
    0.38
     drastic
    0.37
     using
    0.37
    sendStatus
    0.35
    method
    0.35
     Sel
    0.35
     cure
    0.34
     spite
    0.34
    Activations Density 0.963%

    No Known Activations