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

    Neuronpedia

    Jacobian LensNEW
    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. 30-GEMMASCOPE-RES-16K
    11. 10053
    Prev
    Next
    INDEX
    Explanations

    phrases related to popularity and widespread usage

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

    Follows "most" or "widely"

    np_acts-logits-general · gemini-2.0-flash

    widely used and popular

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.59
    __":
    -0.56
    __":
    -0.50
     TextAppearance
    -0.50
    __':
    -0.49
    出版年
    -0.49
    StateException
    -0.45
    initState
    -0.44
    RemoveField
    -0.44
    الدراسه
    -0.43
    POSITIVE LOGITS
     popular
    1.48
    popular
    1.27
    Popular
    1.15
     popularity
    1.14
     Popular
    1.10
     widely
    1.08
     популяр
    1.07
     POPULAR
    1.07
     populaire
    1.04
     loved
    1.02
    Activations Density 0.483%

    No Known Activations