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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 6374
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and personal reflections on interactions and relationships

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

    "I" or personal experiences

    np_acts-logits-general · gemini-2.0-flash

    personal third-person male pronoun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iade
    -0.54
     resourceCulture
    -0.53
    fromnode
    -0.53
    Referencie
    -0.53
    原始内容存档于
    -0.51
     consultato
    -0.50
    ằm
    -0.49
    Datagram
    -0.49
     Dip
    -0.48
    transQ
    -0.48
    POSITIVE LOGITS
     him
    1.01
    him
    0.81
     معه
    0.81
     onun
    0.81
    被他
    0.79
    看着他
    0.76
     ihm
    0.75
     ему
    0.74
    argli
    0.74
     kepad
    0.72
    Activations Density 0.269%

    No Known Activations