© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27722
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and expressions of subjective experiences

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

    I or we doing something

    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
    Personendaten
    -1.02
     برانيه
    -0.76
     Numerade
    -0.74
    UserScript
    -0.71
    IBOutlet
    -0.71
    存于互联网档案馆
    -0.70
     Administrativna
    -0.69
     itſelf
    -0.68
    findpost
    -0.67
    :✨
    -0.67
    POSITIVE LOGITS
    更是
    0.49
     alone
    0.47
    fromnode
    0.47
    pygame
    0.47
     alene
    0.46
     focus
    0.45
    cherichia
    0.45
    wieder
    0.45
    NOST
    0.44
    peño
    0.44
    Activations Density 0.073%

    No Known Activations