© 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. 5-GEMMASCOPE-RES-16K
    11. 7048
    Prev
    Next
    INDEX
    Explanations

    sentences that involve user-centric language, particularly referring to the audience as "you."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.67
    onalds
    -0.63
     Mazar
    -0.58
     חיצוניים
    -0.58
    umab
    -0.57
    saraba
    -0.57
    adda
    -0.56
     Tats
    -0.55
    ształ
    -0.54
     réelle
    -0.53
    POSITIVE LOGITS
    +:+
    0.65
     Chwiliwch
    0.55
    جغرافيا
    0.55
     TQ
    0.54
    xaml
    0.51
     onAnimation
    0.49
    brium
    0.47
    writeField
    0.47
     Stedman
    0.47
    __);
    0.44
    Activations Density 0.213%

    No Known Activations