© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5471
    Prev
    Next
    INDEX
    Explanations

    instances of the word "title" and its variations

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

    the word "title" or references to titles in code or text contexts.

    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
    üyada
    -0.54
     monks
    -0.53
     Greg
    -0.49
     WaitForSeconds
    -0.48
     Cong
    -0.48
     Abar
    -0.47
    monk
    -0.47
     PSC
    -0.47
     Vans
    -0.47
     PX
    -0.47
    POSITIVE LOGITS
     title
    1.36
    title
    1.30
     Title
    1.28
    Title
    1.27
     getTitle
    1.24
    getTitle
    1.20
     TITLE
    1.20
     Titel
    1.07
    TITLE
    1.04
     titles
    1.01
    Activations Density 0.028%

    No Known Activations