© 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. 20-GEMMASCOPE-RES-16K
    11. 1283
    Prev
    Next
    INDEX
    Explanations

    references to health conditions and medical incidents

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

    Following verbs of assistance and movement

    np_acts-logits-general · gemini-2.0-flash

    transporting or helping entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    TypedDataSet
    -0.63
    ьаж
    -0.63
     nakalista
    -0.58
    évaluateur
    -0.56
    NameInMap
    -0.53
    脚注の使い方
    -0.53
     CreateTagHelper
    -0.52
    $_['
    -0.52
    AutoScaleMode
    -0.51
    
    -0.51
    POSITIVE LOGITS
     helping
    0.86
     caring
    0.82
     escort
    0.81
     rescuing
    0.78
     ayud
    0.78
     protecting
    0.78
     transporting
    0.77
    helping
    0.75
     protects
    0.73
     Helping
    0.73
    Activations Density 0.256%

    No Known Activations