© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 53222
    Prev
    Next
    INDEX
    Explanations

    references to self-perception and self-importance

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

    ego and arrogance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     edades
    -0.46
     pengantin
    -0.39
     Jerusalén
    -0.38
    œurs
    -0.38
     Détails
    -0.38
    vědět
    -0.37
    vejec
    -0.36
    jména
    -0.36
     Inglaterra
    -0.35
    jangkau
    -0.35
    POSITIVE LOGITS
    OGND
    0.58
     betweenstory
    0.55
     ego
    0.52
     claim
    0.52
     Ego
    0.51
    RTCK
    0.50
    SourceChecksum
    0.50
     arrogance
    0.49
    claim
    0.49
     arrogant
    0.48
    Activations Density 0.041%

    No Known Activations