© 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. 7987
    Prev
    Next
    INDEX
    Explanations

    phrases or references indicating significant societal or cultural influence

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

    "in the"

    np_acts-logits-general · gemini-2.0-flash

    in the world

    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
     SafeMath
    -0.77
     تضيفلها
    -0.70
     mxArray
    -0.69
    曖昧さ回避
    -0.67
     يتيمه
    -0.64
    AxisAlignment
    -0.63
     WaitForSeconds
    -0.62
    ''')
    -0.59
    })`
    -0.59
    styleType
    -0.57
    POSITIVE LOGITS
     entire
    1.04
     whole
    0.93
    entire
    0.87
    whole
    0.85
     ENTIRE
    0.85
     ever
    0.84
    Entire
    0.81
     Entire
    0.79
     history
    0.79
    Whole
    0.78
    Activations Density 0.111%

    No Known Activations