© 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. 21-GEMMASCOPE-RES-16K
    11. 13583
    Prev
    Next
    INDEX
    Explanations

    phrases expressing personal intentions and actions

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

    first-person singular statements expressing the writer’s actions, states, abilities, or intentions.

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab

    first-person pronouns

    np_max-act-logits · gpt-5Triggered by @arielgoldsteinlab
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     themſelves
    -0.57
     itſelf
    -0.56
     themselves
    -0.54
     resultCode
    -0.53
     förr
    -0.48
    rões
    -0.46
     communautaire
    -0.45
     hjelp
    -0.45
     själva
    -0.45
    قایناق‌لار
    -0.45
    POSITIVE LOGITS
     myself
    1.05
    myself
    0.89
     Myself
    0.80
     I
    0.78
     my
    0.78
    Myself
    0.77
     am
    0.64
     أنا
    0.64
    I
    0.62
    我自己
    0.61
    Activations Density 1.445%

    No Known Activations