© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 14608
    Prev
    Next
    INDEX
    Explanations

    conversations about personal identity and self-perception

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

    'i am', 'you are', 'we are'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     CreateTagHelper
    -0.57
    évaluateur
    -0.51
    WithIOException
    -0.45
    ScopeManager
    -0.43
    ymce
    -0.40
     CGRect
    -0.38
    TagHelper
    -0.38
     QtCore
    -0.37
    rizona
    -0.37
    AxisAlignment
    -0.37
    POSITIVE LOGITS
     somos
    0.91
    我们是
    0.84
     jesteśmy
    0.79
    自己是
    0.77
    我是
    0.75
     jestem
    0.72
     jesteś
    0.68
    你是
    0.67
    他是
    0.66
     êtes
    0.64
    Activations Density 0.120%

    No Known Activations