© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 66545
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal relationships and emotional connections

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

    profanity and negative sentiment

    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
    ſelves
    -0.68
    MigrationBuilder
    -0.67
    EDEFAULT
    -0.63
     betweenstory
    -0.63
     queſta
    -0.61
    ⟬
    -0.60
    DeleteBehavior
    -0.59
    tvguidetime
    -0.59
     itſelf
    -0.59
     ainfi
    -0.58
    POSITIVE LOGITS
     Chwiliwch
    0.38
     goddamn
    0.37
     fucking
    0.36
     fuck
    0.34
     FUCKING
    0.33
     murdering
    0.32
     freaking
    0.32
     tan
    0.31
     bar
    0.31
    OwnProperty
    0.31
    Activations Density 0.154%

    No Known Activations