© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 31118
    Prev
    Next
    INDEX
    Explanations

    concepts related to moral or ethical values

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

    experience and its aspects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.95
     ujednoznacz
    -0.94
     esetén
    -0.88
    ⓧ
    -0.71
    gendes
    -0.68
     дописавши
    -0.67
     Majefty
    -0.66
    НИК
    -0.65
    UserScript
    -0.65
     Houſe
    -0.65
    POSITIVE LOGITS
     itself
    1.03
     of
    0.86
    itself
    0.84
     portion
    0.79
     suivantes
    0.78
     Itself
    0.68
    iniest
    0.67
     שלו
    0.67
    iest
    0.66
     aspect
    0.65
    Activations Density 4.044%

    No Known Activations