© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 4287
    Prev
    Next
    INDEX
    Explanations

    first-person plural pronouns and related collective actions

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

    the first-person plural pronoun "we" and related words indicating collective perspective or group agency.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conmigo
    -1.14
     comigo
    -0.90
     мне
    -0.60
     me
    -0.60
     mnie
    -0.59
     Itself
    -0.59
    私に
    -0.58
    ándome
    -0.57
    給我
    -0.56
     benim
    -0.56
    POSITIVE LOGITS
     ourselves
    2.20
     можем
    1.13
     our
    1.03
     máme
    0.94
     jesteśmy
    0.93
     możemy
    0.92
     знаем
    0.92
     będziemy
    0.91
    我们的
    0.88
    我們的
    0.88
    Activations Density 1.166%

    No Known Activations