© 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. 24-GEMMASCOPE-RES-16K
    11. 3746
    Prev
    Next
    INDEX
    Explanations

    instructions related to dog training and behavioral management

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

    Followed by "your" or "yourself"

    np_acts-logits-general · gemini-2.0-flash

    explain why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleno
    -0.36
     výro
    -0.33
     génie
    -0.33
    其
    -0.33
    werb
    -0.32
    众多
    -0.32
     révélé
    -0.32
    basicConfig
    -0.30
     revelou
    -0.30
    видно
    -0.29
    POSITIVE LOGITS
     your
    0.89
     yourself
    0.85
    ItemBackground
    0.78
    your
    0.70
    :✨
    0.69
    yourself
    0.68
    OGND
    0.66
    AccessorTable
    0.65
     yours
    0.63
    AddTagHelper
    0.63
    Activations Density 0.251%

    No Known Activations