© 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. 4251
    Prev
    Next
    INDEX
    Explanations

    elements related to karaoke activities and social gatherings

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

    product descriptions and uses, with a focus on entertainment and multi-purpose items.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered 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
    
    -0.69
    parsedMessage
    -0.65
    脚注の使い方
    -0.61
     ObjectParameter
    -0.55
    škoda
    -0.54
    ikusbot
    -0.51
     FormData
    -0.50
     estekak
    -0.50
    PerformLayout
    -0.49
     esternos
    -0.49
    POSITIVE LOGITS
     living
    0.43
     prêtres
    0.37
    #+#
    0.34
     Verhältnisse
    0.34
    awsze
    0.33
     CanadaChoose
    0.33
     Morley
    0.33
     בכל
    0.33
     Living
    0.33
     birthdays
    0.33
    Activations Density 0.020%

    No Known Activations