© 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. 20-GEMMASCOPE-RES-16K
    11. 228
    Prev
    Next
    INDEX
    Explanations

    phrases related to compensation or funding matters

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

    "compens" or "up for"

    np_acts-logits-general · gemini-2.0-flash

    compensate for

    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
     Paglinawan
    -0.63
    FormBorderStyle
    -0.61
    /*
    -0.57
    قایناق‌لار
    -0.56
     ProtoMessage
    -0.56
    esez
    -0.54
    writeFieldEnd
    -0.54
    StandardCharsets
    -0.53
    Хьажоргаш
    -0.52
    بینی
    -0.52
    POSITIVE LOGITS
     compensate
    2.32
     compens
    2.18
     compensated
    2.10
     compensating
    2.10
    compens
    2.08
     Compens
    2.08
     compensation
    2.02
     compensatory
    1.90
     компен
    1.89
    compensation
    1.82
    Activations Density 0.230%

    No Known Activations