© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 15759
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the word "you" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mathis
    -0.47
     origine
    -0.47
    math
    -0.47
    HASH
    -0.45
    ass
    -0.45
     lingua
    -0.44
     hashCode
    -0.43
    endung
    -0.43
     исполнитель
    -0.43
     sangue
    -0.42
    POSITIVE LOGITS
     كومونز
    0.88
    wixt
    0.86
    httphttps
    0.85
    Vidite
    0.85
    haustible
    0.84
    Tikang
    0.80
     nahilalakip
    0.79
    ViewFeatures
    0.79
    }}]{
    0.77
    ClientSize
    0.76
    Activations Density 0.130%

    No Known Activations