© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 5313
    Prev
    Next
    INDEX
    Explanations

    terms related to engagement and participation

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

    "engage" and its forms

    np_acts-logits-general · gemini-2.0-flash

    engage with or in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     referenties
    -1.04
    bootstrapcdn
    -0.86
    bewerken
    -0.84
    Manbalar
    -0.83
    thâu
    -0.79
     autorytatywna
    -0.77
     betweenstory
    -0.76
    WriteLiteral
    -0.76
    Билгалдахарш
    -0.76
     bezeichneter
    -0.76
    POSITIVE LOGITS
     engage
    1.39
     engagement
    1.37
     engaged
    1.37
     Engage
    1.32
    engagement
    1.28
    engaged
    1.27
    Engagement
    1.26
     engages
    1.25
     Engagement
    1.24
    engage
    1.21
    Activations Density 0.079%

    No Known Activations