© 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. 28-GEMMASCOPE-RES-16K
    11. 4068
    Prev
    Next
    INDEX
    Explanations

    technical terms related to mechanical devices and their functionalities

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

    Followed by "a," "an," "the," or punctuation

    np_acts-logits-general · gemini-2.0-flash

    legal and technical descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DataAnnotations
    -0.49
     rusty
    -0.49
     clunky
    -0.48
     — 
    -0.48
    =#
    -0.47
     mish
    -0.47
     muddy
    -0.47
    +#+#
    -0.46
     Cit
    -0.45
     MOT
    -0.45
    POSITIVE LOGITS
     dergleichen
    0.61
     hereinafter
    0.59
     wherein
    0.59
     therefrom
    0.58
     Vielzahl
    0.57
     således
    0.57
     herein
    0.53
     aldus
    0.53
     aforesaid
    0.53
     thereof
    0.52
    Activations Density 2.625%

    No Known Activations